[{"data":1,"prerenderedAt":3418},["ShallowReactive",2],{"site-nav-content":3,"hub:compare:posts":178,"site-cta-content":3386,"hiring-banner-content":3406},{"header":4,"productNav":9,"nav":42,"footer":61,"askAI":131,"id":162,"title":163,"archived":164,"authors":165,"badge":165,"body":166,"date":165,"definedTerm":165,"department":165,"description":170,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":130,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":174,"relatedHeading":165,"seo":175,"series":165,"sitemap":164,"status":165,"stem":176,"subhead":165,"tags":165,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":177},{"productLabel":5,"loginLabel":6,"contactLabel":7,"contactSalesLabel":8},"Product","Log in","Contact","Get started for free",[10,14,18,22,26,30,34,38],{"label":11,"to":12,"description":13},"Overview","/overview","Seven layers. One closed loop.",{"label":15,"to":16,"description":17},"Conflux","/product/conflux","Where your team, workstreams, and agents meet.",{"label":19,"to":20,"description":21},"Agent Teams","/product/agent-teams","Specialist teams - governed from day one.",{"label":23,"to":24,"description":25},"Lifecycle Graph","/product/lifecycle-graph","Intelligence that compounds across every interaction.",{"label":27,"to":28,"description":29},"Company Wiki","/product/wiki","Playbooks and policies where expertise stays.",{"label":31,"to":32,"description":33},"Workstreams","/product/workstreams","From brief to signed-off deliverable on one canvas.",{"label":35,"to":36,"description":37},"Perception Console","/product/perception","Ask your whole business in plain English.",{"label":39,"to":40,"description":41},"Governance","/product/governance","Frontier AI you can actually sign off on.",[43,46,49,52,55,58],{"label":44,"to":45},"Models","/models",{"label":47,"to":48},"Pricing","/pricing",{"label":50,"to":51},"Integrations","/integrations",{"label":53,"to":54},"Security","/security",{"label":56,"to":57},"Partners","/partners",{"label":59,"to":60},"Insights","/blog",{"productHeading":5,"companyHeading":62,"legalHeading":63,"docsLabel":64,"docsUrl":65,"statementLines":66,"copyright":69,"companyLinks":70,"legalLinks":100,"socialLinks":110,"bottomLinks":120},"Company","Legal","Docs","https://docs.gonimbus.ai",[67,68],"Stop training someone else's model.","Control your AI.","© 2026 Nimbus Intelligence, Inc. All rights reserved.",[71,72,73,74,75,78,81,84,87,90,92,95,98],{"label":47,"to":48},{"label":50,"to":51},{"label":53,"to":54},{"label":59,"to":60},{"label":76,"to":77},"Glossary","/glossary",{"label":79,"to":80},"Compare","/compare",{"label":82,"to":83},"Evaluate","/evaluate",{"label":85,"to":86},"Problems","/problems",{"label":88,"to":89},"Use cases","/use-cases",{"label":91,"to":57},"Partner Program",{"label":93,"to":94},"Careers","/careers",{"label":96,"to":97},"System status","/status",{"label":7,"to":99},"/contact",[101,104,107],{"label":102,"to":103},"Terms of Service","/terms",{"label":105,"to":106},"Privacy Policy","/privacy",{"label":108,"to":109},"Compliance","/compliance",[111,114,117],{"label":112,"href":113},"LinkedIn","https://www.linkedin.com/company/gonimbusai/",{"label":115,"href":116},"X","https://x.com/gonimbusai",{"label":118,"href":119},"Instagram","https://www.instagram.com/gonimbus_ai/",[121,123,125,126,127],{"label":122,"to":103},"Terms",{"label":124,"to":106},"Privacy",{"label":108,"to":109},{"label":96,"to":97},{"label":128,"to":129,"external":130},"LLMs.txt","/llms.txt",true,{"text":132,"prompt":133},"Ask AI about Nimbus",{"I'm researching enterprise intelligence platforms and want to know how Nimbus combines perception, collaboration, and autonomous agents to drive strategic decision-making":134,"platforms":136},{" Summarize the highlights from Nimbus's website":135},"https://gonimbus.ai",[137,142,147,152,157],{"name":138,"label":139,"icon":140,"hrefPrefix":141},"chatgpt","ChatGPT","simple-icons:openai","https://chatgpt.com/?prompt=",{"name":143,"label":144,"icon":145,"hrefPrefix":146},"perplexity","Perplexity","mdi:magnify","https://www.perplexity.ai/search/new?q=",{"name":148,"label":149,"icon":150,"hrefPrefix":151},"grok","Grok","simple-icons:x","https://x.com/i/grok?text=",{"name":153,"label":154,"icon":155,"hrefPrefix":156},"claude","Claude","simple-icons:anthropic","https://claude.ai/new?q=",{"name":158,"label":159,"icon":160,"hrefPrefix":161},"google-ai","Google AI","simple-icons:google","https://www.google.com/search?udm=50&aep=11&q=","content/shared/nav.md","Site navigation",false,null,{"type":167,"value":168,"toc":169},"minimark",[],{"title":170,"searchDepth":171,"depth":171,"links":172},"",2,[],"md","/shared/nav",{"title":163,"description":170},"shared/nav","rDEv5cVG6P2l9ATcdQv2n6VOQiSL5ioOutyfvGevcD0",[179,566,911,1204,1512,1827,2156,2445,2754,3067],{"id":180,"title":181,"archived":164,"authors":165,"badge":182,"body":187,"date":555,"definedTerm":165,"department":165,"description":556,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":164,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":557,"relatedHeading":165,"seo":558,"series":559,"sitemap":130,"status":165,"stem":560,"subhead":165,"tags":561,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":565},"content/blog/nimbus-vs-chatgpt-enterprise.md","Nimbus vs ChatGPT Enterprise: The Assistant You Love vs the Place Work Gets Recorded",{"label":183,"10|authors":184},"Comparisons",[185],{"name":186,"to":135},"Nimbus Research",{"type":167,"value":188,"toc":535},[189,200,212,220,225,276,280,283,286,303,310,318,325,333,337,340,343,346,357,361,368,397,404,412,416,421,428,432,435,439,442,446,452,456,459,463,466,470,473,477,480,484,487,491,505,509],[190,191,192,199],"p",{},[193,194,198],"a",{"href":195,"rel":196},"https://openai.com/business/chatgpt-enterprise/",[197],"nofollow","ChatGPT Enterprise"," (and ChatGPT Business for smaller teams) is OpenAI’s hosted assistant for work: company login, retention controls, and a chat people already know. Nimbus is the place that draft becomes a company action — with a named signer and a record you can reconstruct next quarter. You can keep both. ChatGPT is how people think. Nimbus is how the organisation finishes the job.",[190,201,202,203,207,208,211],{},"That split is easy to miss because both products talk about agents, connectors, and knowledge. The jobs are still different. ChatGPT Enterprise is a governed ",[204,205,206],"em",{},"assistant",": a place knowledge workers already open, with admin, SSO, and a processing agreement. Nimbus is a governed ",[204,209,210],{},"operating layer",": a place a job lives until someone signs a change in a live system. Treat those as one purchase and you will either under-buy the assistant people actually use, or under-buy the ledger finance actually needs.",[190,213,214,219],{},[193,215,218],{"href":216,"rel":217},"https://openai.com/enterprise-privacy/",[197],"OpenAI’s enterprise privacy page"," is the promise that matters for the assistant: OpenAI does not train on Enterprise or Business data by default, and customers control retention. That closes the “personal Plus account on the side” hole. It is not a ledger of what changed in your CRM. Closing shadow chat is a real win. Reconstructing a signed customer-record change is a different win. Most organisations need both, in that order: stop the unofficial accounts, then decide where work that mutates systems of record is allowed to finish.",[221,222,224],"h2",{"id":223},"words-youll-hear","Words you’ll hear",[226,227,228,236,242,248,254,260,266],"ul",{},[229,230,231,235],"li",{},[232,233,234],"strong",{},"ChatGPT Enterprise / Business."," The official company tenant of ChatGPT, with admin, SSO, and a processing agreement.",[229,237,238,241],{},[232,239,240],{},"Company knowledge."," Permission-aware search over workplace sources such as Slack, Drive, SharePoint, Notion, GitHub, HubSpot, and Zendesk before the model answers.",[229,243,244,247],{},[232,245,246],{},"Workspace Agents."," Team-owned agents inside ChatGPT that persist across sessions, can run in the background, and use native connectors. They are off by default; admins enable them with role-based access.",[229,249,250,253],{},[232,251,252],{},"Workstream."," In Nimbus, a shared workspace for one job — people, tools, budget, and a finish line — not a chat thread.",[229,255,256,259],{},[232,257,258],{},"Write-back."," Changing a live system (a CRM field, a journal). In Nimbus, connectors stay read-only until a named person signs the exact change.",[229,261,262,265],{},[232,263,264],{},"Lifecycle Graph."," Nimbus’s causal record of what ran, who approved it, and what changed.",[229,267,268,271,272,275],{},[232,269,270],{},"Compliance Platform."," OpenAI’s feed of ChatGPT logs and metadata for eDiscovery, DLP, or SIEM. Useful. Still a feed of what happened ",[204,273,274],{},"inside ChatGPT",".",[221,277,279],{"id":278},"why-the-difference-matters","Why the difference matters",[190,281,282],{},"Everyone using ChatGPT is not the same as the company being able to explain last quarter.",[190,284,285],{},"ChatGPT Enterprise is good at the job OpenAI designed it for. People already know the product. IT can put it behind company login. Retention is a customer control rather than a rumour. Company knowledge is the right design if the failure is “the model answered from a file this person could not open.” Workspace Agents persist, can run in the background, and use native connectors, with admins deciding who may turn them on. None of that is trivial. It is why so many organisations standardise on ChatGPT as the default thinking surface.",[190,287,288,289,292,293,298,299,302],{},"The limit is what that surface is ",[204,290,291],{},"for",". Ask: “Show me every customer-record change an agent proposed last quarter, who approved it, and what our playbook said.” OpenAI’s ",[193,294,297],{"href":295,"rel":296},"https://help.openai.com/en/articles/9261474",[197],"Compliance Platform"," gives Enterprise and Edu customers logs from the ChatGPT workspace — useful for eDiscovery, DLP, or a SIEM. Reconstructing ",[204,300,301],{},"your"," Salesforce changes as a business event — across go-to-market and finance, with the signed-off version attached — is a different job. A feed of what happened inside ChatGPT is not a ledger of what happened in the CRM.",[190,304,305,306,309],{},"Company knowledge is permission-aware retrieval. That answers “did this person have a right to see that file?” Limits show up when the same fact lives in Slack, a deck, and a CRM field with no official owner — and when last quarter’s ",[204,307,308],{},"decision"," never became a document. Search cannot invent a signer.",[190,311,312,313,317],{},"Writes exist in ChatGPT; they are gated by admin policy and often by a per-action confirmation. That is productivity with confirmation fatigue. Nimbus treats the write as a ",[193,314,316],{"href":315},"what-is-write-back-governance","release",": quote the change, name the signer, store the outcome. Confirmation is a courtesy. A quoted release is a control.",[190,319,320,321,324],{},"Seat price plus credits for Workspace Agents is a real cost line. Every team inventing agents is spend and a risk surface, and a “just use the flagship model” default burns frontier prices on small tasks. Nimbus meters work in NTUs (work credits) and ",[193,322,323],{"href":45},"routes models"," so routine steps do not consume frontier prices. Compare whether you can attribute spend to a job — not only which seat looks cheaper.",[190,326,327,328,332],{},"The fork is practical by role. A knowledge worker wants a chat they already know, with company files in reach — ChatGPT Enterprise is that product. RevOps wants to know which opportunity fields an agent proposed, who signed, and which playbook version applied. Finance wants a named signer on anything that touches revenue or journals; a Compliance Platform feed shows ChatGPT usage, not a CRM release. Security and legal want SSO, retention, and a processing agreement for the assistant, and still want purpose limitation when recruiting must not see finance forecasts. IT will run identity, company-knowledge crawls, and agent design: a real programme, and not the same programme as standing up workstreams. An official ChatGPT workspace is how you stop people pasting customer data into personal accounts — better than ",[193,329,331],{"href":330},"what-is-shadow-ai","shadow AI",". Nimbus is how you stop the next failure: the draft that became a live field with nobody on the change.",[221,334,336],{"id":335},"when-chatgpt-enterprise-is-a-better-fit","When ChatGPT Enterprise is a better fit",[190,338,339],{},"Choose ChatGPT Enterprise when the job is a governed assistant for knowledge workers, company knowledge over Drive and Slack is the main AI win, and you want OpenAI as both model vendor and the place people work.",[190,341,342],{},"Choose Workspace Agents when the work should live in ChatGPT or Slack and confirmation-gated connector actions are enough. If the team is writing briefs, summarising threads, and drafting from files they can already open, forcing that into a workstream is ceremony.",[190,344,345],{},"Using Nimbus does not mean abandoning ChatGPT. It means ChatGPT stops being the only place work happened. A coherent coexistence looks like this: people keep ChatGPT for personal and team thinking; company knowledge stays the retrieval layer for that assistant; anything that must change a system of record, carry a budget, or be reconstructable next quarter moves into a Nimbus workstream. Drafts can travel. Write credentials should not.",[190,347,348,349,352,353,356],{},"Choose on the verb. If the verb is ",[204,350,351],{},"ask and draft",", ChatGPT. If the verb is ",[204,354,355],{},"release and remember",", Nimbus. Most companies need both verbs.",[221,358,360],{"id":359},"how-this-shows-up-in-nimbus","How this shows up in Nimbus",[190,362,363,364,367],{},"Nimbus can use OpenAI models for a given step. It does not assume ChatGPT is the operating layer. That is ",[193,365,366],{"href":45},"routing",", not a ChatGPT clone.",[190,369,370,371,375,376,380,381,384,385,388,389,392,393,396],{},"Operators open ",[193,372,374],{"href":373},"what-is-an-ai-workstream","workstreams"," themselves. The unit is the job: people, tools, budget, and a finish line. The ",[193,377,379],{"href":378},"what-is-a-company-wiki-for-ai-agents","wiki"," is the playbook agents must follow — a discount floor, a journal policy, a write rule — rather than a prompt someone pasted into a custom GPT. ",[193,382,383],{"href":51},"Connectors"," are read-only until a write is approved. ",[193,386,387],{"href":20},"Agent teams"," are department-shaped specialists on the job. The ",[193,390,23],{"href":391},"what-is-a-lifecycle-graph"," is the record. ",[193,394,395],{"href":36},"Perception"," is how you ask that record in ordinary language — “what did we approve for this account last quarter?”",[190,398,399,400,403],{},"You can ",[193,401,402],{"href":12},"set Nimbus up yourselves",". ChatGPT Enterprise at scale often still looks like a programme — identity, company-knowledge crawls, agent design — with OpenAI or partner engineers in the building. That is a real delivery model. It is not how Nimbus is sold.",[190,405,406,407,409,410,275],{},"See ",[193,408,39],{"href":40}," and the ",[193,411,23],{"href":24},[221,413,415],{"id":414},"questions-people-actually-ask","Questions people actually ask",[417,418,420],"h3",{"id":419},"does-nimbus-compete-with-openai","Does Nimbus compete with OpenAI?",[190,422,423,424,427],{},"At the application layer, yes. At the model layer, no. Nimbus is a customer of frontier models. GPT-class models are often the right choice for a given step — and often they are not. See ",[193,425,426],{"href":45},"models",". Buying Nimbus does not require leaving OpenAI. It requires stopping the assumption that the chat product is the company operating system.",[417,429,431],{"id":430},"can-nimbus-replace-chatgpt-enterprise","Can Nimbus replace ChatGPT Enterprise?",[190,433,434],{},"If ChatGPT usage is a handful of shared GPTs on docs and Slack, a workstream-plus-wiki move is plausible. If you have made ChatGPT the default employee assistant, keep it. Put Nimbus on the business loop where writes, budgets, and the graph matter. Replacing a loved assistant to “standardise on one vendor” is how you recreate shadow Plus accounts.",[417,436,438],{"id":437},"are-workspace-agents-the-same-as-nimbus-agent-teams","Are Workspace Agents the same as Nimbus agent teams?",[190,440,441],{},"No. Workspace Agents are team-owned workers inside OpenAI’s product, with durable memory and native connectors. They persist across sessions and can run in the background; admins enable them with role-based access. Nimbus agent teams are department-shaped operators on a workstream, with playbooks, a release path, and a company record. Shared ownership is the overlap. The work loop is not. One lives in ChatGPT. The other lives on the job.",[417,443,445],{"id":444},"how-do-connector-counts-compare","How do connector counts compare?",[190,447,448,449,275],{},"ChatGPT’s native catalogue is on the order of tens to about 90-plus, plus custom tools. Nimbus publishes 2,000+ integrations, scoped to the workspace and read-only until a write is approved. Count is not the whole story. A connector that can write after a confirmation click is a different risk class from a connector that cannot write until a named person signs a quoted change. See ",[193,450,451],{"href":51},"integrations",[417,453,455],{"id":454},"is-chatgpt-company-knowledge-the-same-as-a-lifecycle-graph","Is ChatGPT company knowledge the same as a Lifecycle Graph?",[190,457,458],{},"No. Company knowledge is an index of files you already have, with each user’s permissions respected. The Lifecycle Graph is a record of work and releases. Collapsing those in a vendor meeting is how you buy search and think you bought memory. Permission-aware retrieval answers “could this person see that file?” A graph answers “who signed this change, and what did the playbook say?”",[417,460,462],{"id":461},"can-we-keep-chatgpt-and-still-put-writes-in-nimbus","Can we keep ChatGPT and still put writes in Nimbus?",[190,464,465],{},"Yes. That is the intended coexistence. People think in ChatGPT. They finish in Nimbus. Do not give Workspace Agents production write credentials “because we already have confirmation prompts,” and do not ban ChatGPT because Nimbus exists. Ban unofficial accounts. Route mutations.",[417,467,469],{"id":468},"what-does-the-compliance-platform-actually-give-us","What does the Compliance Platform actually give us?",[190,471,472],{},"A feed of ChatGPT logs and metadata for eDiscovery, DLP, or SIEM. That is the right artefact if the question is “what happened inside the ChatGPT workspace?” It is the wrong artefact if the question is “what changed in Salesforce, who approved it, and which playbook applied?” Use both questions. Do not let one answer stand in for the other.",[417,474,476],{"id":475},"who-should-own-which-product","Who should own which product?",[190,478,479],{},"IT and the knowledge-worker programme typically own ChatGPT Enterprise: identity, retention, company knowledge, Workspace Agent policy. Line operators — RevOps, finance, shared services — typically own Nimbus workstreams, because they own the systems of record those workstreams touch. Security reviews both.",[417,481,483],{"id":482},"is-confirmation-on-a-connector-action-enough-for-finance","Is confirmation on a connector action enough for finance?",[190,485,486],{},"Usually not, if the change hits revenue, pipeline, or journals. Confirmation is easy to click through and hard to reconstruct. Finance wants a quoted payload, a named signer, and a stored outcome. If your writes are low-radius and reversible, ChatGPT’s confirmation model may be enough. If they are not, you are specifying a release.",[221,488,490],{"id":489},"related-reading","Related reading",[190,492,493,496,497,500,501,275],{},[193,494,495],{"href":330},"What is shadow AI",", ",[193,498,499],{"href":315},"What is write-back governance",", and ",[193,502,504],{"href":503},"nimbus-vs-claude","Nimbus vs Claude",[221,506,508],{"id":507},"sources","Sources",[226,510,511,516,522,529],{},[229,512,513],{},[193,514,198],{"href":195,"rel":515},[197],[229,517,518],{},[193,519,521],{"href":216,"rel":520},[197],"OpenAI enterprise privacy",[229,523,524],{},[193,525,528],{"href":526,"rel":527},"https://help.openai.com/en/articles/10128477-chatgpt-enterprise-edu-release-notes",[197],"ChatGPT Enterprise & Edu release notes",[229,530,531],{},[193,532,534],{"href":295,"rel":533},[197],"OpenAI Compliance Platform for Enterprise and Edu",{"title":170,"searchDepth":171,"depth":171,"links":536},[537,538,539,540,541,553,554],{"id":223,"depth":171,"text":224},{"id":278,"depth":171,"text":279},{"id":335,"depth":171,"text":336},{"id":359,"depth":171,"text":360},{"id":414,"depth":171,"text":415,"children":542},[543,545,546,547,548,549,550,551,552],{"id":419,"depth":544,"text":420},3,{"id":430,"depth":544,"text":431},{"id":437,"depth":544,"text":438},{"id":444,"depth":544,"text":445},{"id":454,"depth":544,"text":455},{"id":461,"depth":544,"text":462},{"id":468,"depth":544,"text":469},{"id":475,"depth":544,"text":476},{"id":482,"depth":544,"text":483},{"id":489,"depth":171,"text":490},{"id":507,"depth":171,"text":508},"2026-08-17","ChatGPT Enterprise is OpenAI’s hosted work assistant; Nimbus is where a draft becomes a signed company action you can reconstruct later.","/blog/nimbus-vs-chatgpt-enterprise",{"title":181,"description":556},"comparisons","blog/nimbus-vs-chatgpt-enterprise",[559,138,562,563,564],"openai","enterprise-ai","workspace-agents","EAeqdijxddQL9whUFJz7XjCco-JWe3Xr8Z613bYkkxo",{"id":567,"title":568,"archived":164,"authors":165,"badge":569,"body":572,"date":555,"definedTerm":165,"department":165,"description":904,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":164,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":905,"relatedHeading":165,"seo":906,"series":559,"sitemap":130,"status":165,"stem":907,"subhead":165,"tags":908,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":910},"content/blog/nimbus-vs-claude.md","Nimbus vs Claude: A Thinking Partner or a Place Thinking Becomes an Approved Change?",{"label":183,"10|authors":570},[571],{"name":186,"to":135},{"type":167,"value":573,"toc":885},[574,593,596,605,607,654,656,665,668,682,690,697,704,717,720,724,727,730,733,740,742,748,761,766,770,772,776,779,783,793,797,800,804,812,816,819,823,826,830,833,837,840,844,847,849,859,861],[190,575,576,577,580,581,588,589,592],{},"“Claude” is three buying decisions that get collapsed in meetings. The ",[232,578,579],{},"model"," is what you call from your own software. ",[232,582,583],{},[193,584,587],{"href":585,"rel":586},"https://www.anthropic.com/news/claude-for-work",[197],"Claude for Work"," is Anthropic’s hosted assistant: chats, Projects, artifacts, connectors, and admin controls. Claude also shows up ",[232,590,591],{},"inside other products",". Nimbus is none of those. It is the place a strong analysis becomes an approved change in Salesforce, billing, or the policy pack — with a named person on the release.",[190,594,595],{},"This article compares Nimbus to Claude for Work, and to the idea that “we standardised on Claude, so we are done.” The API is complementary: Nimbus can send a step to Claude rather than replacing it. Standardising on a model is not the same as standardising on a place departments finish work.",[190,597,598,599,604],{},"Claude for Work is a serious product. It is built around careful long-context analysis, writing, coding help, and a safety posture enterprises actually cite in questionnaires. Projects give a person or a small team a durable bundle of files and instructions. Artifacts give you something you can look at besides a wall of prose. Connectors and company admin exist because Anthropic knows enterprises will not live in a personal ",[193,600,603],{"href":601,"rel":602},"https://claude.ai",[197],"claude.ai"," tab forever. That is a thinking partner with a workspace. It is still a thinking partner.",[221,606,224],{"id":223},[226,608,609,615,621,627,632,638,643,648],{},[229,610,611,614],{},[232,612,613],{},"Claude for Work."," Anthropic’s hosted workspace: chats, Projects, artifacts, connectors, and company admin.",[229,616,617,620],{},[232,618,619],{},"Project."," A durable bundle of files and instructions in Claude. Excellent context for one person or a small team. Not a company job.",[229,622,623,626],{},[232,624,625],{},"Constitutional AI."," Anthropic’s research on training models to refuse and to be careful. That is model behaviour. It is not a company operating layer.",[229,628,629,631],{},[232,630,252],{}," In Nimbus, a shared workspace for one job, with the people, tools, and approval rules attached.",[229,633,634,637],{},[232,635,636],{},"Wiki."," Official playbooks agents must follow — including a discount floor, a journal policy, or a write rule.",[229,639,640,642],{},[232,641,258],{}," Changing a live system. Connectors stay read-only until a named person signs.",[229,644,645,647],{},[232,646,264],{}," The causal record of what ran, who approved it, and what changed.",[229,649,650,653],{},[232,651,652],{},"Model routing."," Sending each step to the right model. Claude is often right for long, careful writing and wrong for a routine extract.",[221,655,279],{"id":278},[190,657,658,659,664],{},"Claude for Work is excellent at what Anthropic optimises: careful long-context analysis, writing, coding help, and a safety posture enterprises actually cite in questionnaires. ",[193,660,663],{"href":661,"rel":662},"https://www.anthropic.com/legal/privacy",[197],"Anthropic’s privacy policy"," is the product’s own account of how the hosted assistant handles data. Read it as the privacy story for Claude-the-product. It is not a company operating system. Privacy of the assistant and provenance of a company action are related concerns. They are not the same control.",[190,666,667],{},"In Claude, the organisational unit is the conversation (and the Project). Memory is whatever Anthropic’s product retains for that workspace, plus the files you uploaded. When the Project is deleted, or the person leaves, the “memory” is a pile of chats. That is fine for analysis that was always meant to be personal or small-team. It is fragile for a discount exception that finance must still explain in two years.",[190,669,670,671,674,675,678,679,681],{},"In Nimbus, the same job is a ",[193,672,673],{"href":373},"workstream",". An ",[193,676,677],{"href":20},"agent team"," drafts against the wiki clause that states the rule. Finance and legal can sit on the same canvas. Customer records stay read-only until a human releases the change. The ",[193,680,23],{"href":391}," keeps what ran, who approved it, and what changed — so next quarter you are not hunting Slack for “the Claude doc.” A Project is context. A signed change is the record.",[190,683,684,689],{},[193,685,688],{"href":686,"rel":687},"https://www.anthropic.com/research/constitutional-ai-harmlessness-from-ai-feedback",[197],"Anthropic’s Constitutional AI"," work is why enterprises cite Claude’s safety posture. The research is about training models to refuse and to be careful. That is valuable. A model that refuses a harmful request is not a named signer on a CRM write. A brilliant Project is still context. Those refusals still do not give you a company operating layer. Do not let a safety questionnaire stand in for a release process.",[190,691,692,693,696],{},"If the executive summary is “we bought Claude, therefore we have enterprise AI,” you have bought a model and a workspace. You have not bought a place departments finish work. That gap is where people start pasting Claude output straight into Salesforce — ungoverned ",[193,694,695],{"href":315},"write-back"," with extra steps. Careful analysis that becomes an unsigned field is still an unsigned field.",[190,698,699,700,275],{},"Claude’s long context is a model feature. A Lifecycle Graph is a product feature. Do not confuse a very large window with ",[193,701,703],{"href":702},"what-is-institutional-memory-in-enterprise-ai","institutional memory",[190,705,706,707,711,712,716],{},"The fork is practical by role. Analysts, counsel, and writers get a thinking partner that is unusually good at long documents — Claude for Work is often the right daily surface. Engineers may want the Claude API so they can own orchestration, evaluation, and tool policy: a build, not an operating layer for operators. RevOps and finance need the analysis to land as a quoted change with a signer, not another Project named after last quarter’s close. Security will like Constitutional AI as a model-behaviour story and still ask who can change production records. A COO should not be told that desktop and coding agents (Claude Cowork and similar) are the company AI programme; those personal runtimes are closer to ",[193,708,710],{"href":709},"nimbus-vs-openclaw","OpenClaw"," or ",[193,713,715],{"href":714},"nimbus-vs-hermes","Hermes"," than to a company operating layer.",[190,718,719],{},"The job split is therefore: Claude thinks; Nimbus finishes. You can use Claude as the model behind a Nimbus step. You should not use a Claude Project as the system of record for a decision that hit the CRM.",[221,721,723],{"id":722},"when-claude-is-a-better-fit","When Claude is a better fit",[190,725,726],{},"Choose Claude for Work when the job is high-quality reasoning and writing on documents you can put in a Project, you do not need gated writes into the systems that hold customer and money data, and you want Anthropic as both model vendor and the place people work.",[190,728,729],{},"Choose the Claude API when you have engineers to own orchestration, evaluation, and tool policy. That path is honest: you are building. Do not pretend the API is a workstream product with a wiki and a graph.",[190,731,732],{},"Desktop and coding agents (Claude Cowork and similar) are personal runtimes. Choose them for a person who will look after their own machine. Do not standardise the company on them and call it governance.",[190,734,735,736,739],{},"Using Nimbus does not mean abandoning Claude. It means Claude stops being the place the company thinks the work finished. A healthy coexistence: people keep Claude for careful analysis; Nimbus routes some steps ",[204,737,738],{},"to"," Claude when the task is long, careful writing; anything that must change Salesforce, billing, or the policy pack is a workstream with a signer. Paste is a last resort, not the integration.",[221,741,360],{"id":359},[190,743,744,745,747],{},"Nimbus is not a Claude competitor in the model sense. Claude is often the right model for long, careful writing. It is the wrong default for a routine extract, and the wrong abstraction for “how we run AI at work.” See ",[193,746,426],{"href":45},". Routing is how you avoid using the most expensive model for every small task, and how you keep Claude in the loop without making Claude the loop.",[190,749,750,751,753,754,757,758,760],{},"Nimbus keeps three planes operators actually run: asserted policy (",[193,752,379],{"href":28},"), live systems (",[193,755,756],{"href":51},"connectors",", read-only by default), and derived memory (Lifecycle Graph). ",[193,759,395],{"href":36}," lets anyone ask in ordinary language — “what did we approve for this account last quarter?” — without hoping someone named the chat correctly. That is the opposite of a Project whose title only the author remembers.",[190,762,399,763,765],{},[193,764,402],{"href":12},". You are not waiting on vendor engineers to invent an operating layer around Claude. If you already have Claude for Work, keep it. Attach the systems of record in Nimbus. Put the playbook in the wiki. Let Claude draft; let a human release.",[190,767,406,768,275],{},[193,769,39],{"href":40},[221,771,415],{"id":414},[417,773,775],{"id":774},"does-nimbus-compete-with-anthropic","Does Nimbus compete with Anthropic?",[190,777,778],{},"At the application layer, yes. At the model layer, no. Nimbus is a customer of frontier models. Routing is how you avoid using the most expensive model for every small task. A Claude-shaped step inside a workstream is complementarity. A Claude Project used as the company archive is substitution you will regret.",[417,780,782],{"id":781},"can-i-bring-my-own-claude-api-key","Can I bring my own Claude API key?",[190,784,785,786,789,790,275],{},"Model routing and bring-your-own-key options are part of how Nimbus treats models as infrastructure. Talk to ",[193,787,788],{"href":99},"sales"," for the current enterprise path. Do not assume a one-to-one replica of Anthropic’s consumer chat inside Nimbus; the experience is workstreams and Perception, not a clone of ",[193,791,603],{"href":601,"rel":792},[197],[417,794,796],{"id":795},"is-nimbus-just-a-wrapper-on-claude","Is Nimbus “just a wrapper on Claude”?",[190,798,799],{},"No. A wrapper is a chat window. Nimbus ships a Lifecycle Graph, specialist agent teams, and a read-only-default path for changing records. If the model behind a step is Claude, that is routing, not wrapping. If you removed Claude and routed the same step elsewhere, the workstream, wiki, and graph would still be there.",[417,801,803],{"id":802},"claude-vs-chatgpt-enterprise-vs-nimbus","Claude vs ChatGPT Enterprise vs Nimbus?",[190,805,806,807,811],{},"Claude and ChatGPT are rival assistants (and rival APIs). Nimbus can sit on either. Shortlist Anthropic vs OpenAI on model and workspace grounds — writing quality, safety posture, company knowledge, Workspace Agents versus Projects. Shortlist Nimbus when the work includes production writes and a ledger. See ",[193,808,810],{"href":809},"nimbus-vs-chatgpt-enterprise","Nimbus vs ChatGPT Enterprise",". Buying the assistant bake-off and skipping the operating-layer question is how you end up with two chats and still no signer.",[417,813,815],{"id":814},"will-claude-for-work-update-salesforce-for-us","Will Claude for Work update Salesforce for us?",[190,817,818],{},"Not as a release manager for enterprise writes. Thinking in Claude and pasting into Salesforce is productivity. It is also drift. If the plan is “an agent team drafts, a human releases, the graph stores the artefact,” you are specifying Nimbus — and you can still use Claude as the model behind the draft.",[417,820,822],{"id":821},"is-a-project-the-same-as-a-workstream","Is a Project the same as a workstream?",[190,824,825],{},"No. A Project is a durable bundle of files and instructions. Excellent context for one person or a small team. A workstream is a shared workspace for one job, with people, tools, approval rules, a budget, and a finish line. Projects do not give you connector-level least privilege, quoted writes, or a Lifecycle Graph. Useful for research. Not an operations unit.",[417,827,829],{"id":828},"does-constitutional-ai-mean-we-can-skip-write-back-gates","Does Constitutional AI mean we can skip write-back gates?",[190,831,832],{},"No. Constitutional AI is model behaviour: refusal and care in training. Write-back governance is a product control: the connector cannot write until a named person signs the quoted change. A careful model can still propose a bad field update. The gate is what stops the proposal becoming a fact.",[417,834,836],{"id":835},"can-we-use-claude-for-work-beside-nimbus-without-duplicating-memory","Can we use Claude for Work beside Nimbus without duplicating memory?",[190,838,839],{},"Yes, if you are strict about what each remembers. Claude remembers the analysis in a Project. Nimbus remembers the job, the playbook version, the signer, and the change. Do not copy the CRM into a Project “for context” and then treat that copy as official. Point at the live system from the workstream.",[417,841,843],{"id":842},"who-owns-claude-vs-who-owns-nimbus","Who owns Claude vs who owns Nimbus?",[190,845,846],{},"Knowledge workers and often legal or research own Claude for Work as a thinking surface. Engineers may own the API. Operators who own systems of record own Nimbus workstreams. Security reviews both.",[221,848,490],{"id":489},[190,850,851,496,853,500,857,275],{},[193,852,499],{"href":315},[193,854,856],{"href":855},"what-is-model-routing","What is model routing",[193,858,810],{"href":809},[221,860,508],{"id":507},[226,862,863,868,873,879],{},[229,864,865],{},[193,866,587],{"href":585,"rel":867},[197],[229,869,870],{},[193,871,603],{"href":601,"rel":872},[197],[229,874,875],{},[193,876,878],{"href":661,"rel":877},[197],"Anthropic privacy policy",[229,880,881],{},[193,882,884],{"href":686,"rel":883},[197],"Anthropic, Constitutional AI",{"title":170,"searchDepth":171,"depth":171,"links":886},[887,888,889,890,891,902,903],{"id":223,"depth":171,"text":224},{"id":278,"depth":171,"text":279},{"id":722,"depth":171,"text":723},{"id":359,"depth":171,"text":360},{"id":414,"depth":171,"text":415,"children":892},[893,894,895,896,897,898,899,900,901],{"id":774,"depth":544,"text":775},{"id":781,"depth":544,"text":782},{"id":795,"depth":544,"text":796},{"id":802,"depth":544,"text":803},{"id":814,"depth":544,"text":815},{"id":821,"depth":544,"text":822},{"id":828,"depth":544,"text":829},{"id":835,"depth":544,"text":836},{"id":842,"depth":544,"text":843},{"id":489,"depth":171,"text":490},{"id":507,"depth":171,"text":508},"Claude is Anthropic’s thinking partner for careful analysis; Nimbus is where that analysis becomes a signed change in the tools you already run.","/blog/nimbus-vs-claude",{"title":568,"description":904},"blog/nimbus-vs-claude",[559,153,909,563,426],"anthropic","gkBctD5JsSfFvv8fqxkZvUEB6K7g7uJij2s-cQPuvls",{"id":912,"title":913,"archived":164,"authors":165,"badge":914,"body":917,"date":555,"definedTerm":165,"department":165,"description":1195,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":164,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":1196,"relatedHeading":165,"seo":1197,"series":559,"sitemap":130,"status":165,"stem":1198,"subhead":165,"tags":1199,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":1203},"content/blog/nimbus-vs-dust.md","Nimbus vs Dust: A Shared Agent Studio or a Place Departments Finish Work?",{"label":183,"10|authors":915},[916],{"name":186,"to":135},{"type":167,"value":918,"toc":1177},[919,927,930,939,941,991,993,996,1010,1013,1028,1034,1037,1040,1044,1047,1053,1056,1058,1061,1066,1072,1078,1080,1084,1087,1091,1096,1100,1103,1107,1110,1114,1117,1121,1124,1128,1131,1135,1138,1140,1150,1152],[190,920,921,926],{},[193,922,925],{"href":923,"rel":924},"https://dust.tt",[197],"Dust"," is a shared agent studio. Your people write agents in plain language, connect them to Slack, Notion, Google Drive, GitHub, Salesforce, Zendesk and other apps, and pick which AI model each agent should use. Nimbus is the place those drafts have to survive contact with the rest of the company: go-to-market, finance, and ops on one job, with a sign-off and a record of what changed.",[190,928,929],{},"Dust’s centre of gravity is the agent itself: create it, share it, run it. Nimbus’s centre of gravity is the job. That is not a slight. Studios are how teams stop trapping a useful helper in one person’s chat history. Jobs are how several departments finish something that still makes sense next quarter. If you buy a studio and expect a ledger, you will be disappointed in the studio. If you buy a work OS and expect a flexible agent workshop as the main experience, you will be disappointed in the OS.",[190,931,932,933,938],{},"Dust is a French company, and that is part of why European buyers look at it closely. GDPR still applies when agents process personal data in company tools. Teams share agents, so the same helper is not trapped in one person’s history. Admins get company sign-in, roles for who can build or run an agent, and activity logs. Engineers can plug Dust agents into other developer tools. Model choice is real: OpenAI, Anthropic, Google, Mistral and others. Dust’s ",[193,934,937],{"href":935,"rel":936},"https://docs.dust.tt/docs/user-documentation/getting-started/dust-rollout-guide/welcome-to-dust",[197],"rollout guide"," describes that studio as an enterprise AI platform connecting models to internal knowledge, tools, and workflows.",[221,940,224],{"id":223},[226,942,943,949,959,965,970,975,980,985],{},[229,944,945,948],{},[232,946,947],{},"Agent studio."," A place to build, share, and run custom agents. Dust’s product. Useful. Not the same as a place several departments finish one job.",[229,950,951,954,955,958],{},[232,952,953],{},"Multiplayer agents."," Dust’s term for agents that are not trapped in one person’s chat history. Real. Still primarily ",[204,956,957],{},"shared agents",", not a lasting record of what finance approved.",[229,960,961,964],{},[232,962,963],{},"Model choice."," Dust works with OpenAI, Anthropic, Google, Mistral and others, so you are not locked to one chatbot brand. Nimbus does the same, and treats the choice as an operating decision: do not use the most expensive model for every small task.",[229,966,967,969],{},[232,968,252],{}," In Nimbus, a shared workspace for one job, with the right people, tools, and approval rules.",[229,971,972,974],{},[232,973,636],{}," Official playbooks agents must follow.",[229,976,977,979],{},[232,978,258],{}," Changing a live system. In Nimbus, connectors stay read-only until a named person signs.",[229,981,982,984],{},[232,983,264],{}," The causal record of what the AI did, who approved it, and what changed.",[229,986,987,990],{},[232,988,989],{},"CNIL."," France’s data-protection authority. Dust is a French company; GDPR still applies when agents process personal data in company tools.",[221,992,279],{"id":278},[190,994,995],{},"Teams can share Dust agents, so the same helper is not trapped in one person’s history. That “multiplayer” claim is fair. Admins get company sign-in, roles for who can build or run an agent, and activity logs. Engineers can plug Dust agents into other developer tools. Dust’s rollout guide is written as a programme: connect models to internal knowledge, tools, and workflows. That is a studio you roll out, not a toy.",[190,997,998,999,674,1001,1003,1004,1006,1007,1009],{},"Whether finance ever sees a discount field depends on how disciplined you were about who can invoke that agent, and whether anyone filed the run somewhere finance actually looks. Activity logs tell you that an agent ran. They do not automatically become a signed-off version of a CRM change. In Nimbus, go-to-market and finance sit on the same ",[193,1000,673],{"href":373},[193,1002,677],{"href":20}," drafts against the ",[193,1005,379],{"href":378},". Customer records stay read-only until someone who is allowed to approve writes actually does. The ",[193,1008,23],{"href":391}," keeps the signed-off version, not only the chat that produced it.",[190,1011,1012],{},"Dust searches connected sources and whatever you put in an agent’s knowledge. That works well when the files are clean. It gets fragile when the same fact lives in Slack, a deck, and a CRM field, and nobody is the official owner. If your failure is “the agent answered from an outdated Notion page,” Dust’s freshness and permission model matter most. If your failure is “we ran this last quarter and nobody can find the version finance signed,” you need a record of the job, not another shared agent.",[190,1014,1015,1016,1021,1022,1027],{},"Because Dust is French, the natural data-protection authority is the ",[193,1017,1020],{"href":1018,"rel":1019},"https://www.cnil.fr/en/ai-system-development-cnils-recommendations-to-comply-gdpr",[197],"CNIL",". CNIL is clear that GDPR still applies when you develop and run AI that processes personal data, including when those systems later connect to company tools. A shared Salesforce agent is not “just a helper.” It is processing with a purpose. ",[193,1023,1026],{"href":1024,"rel":1025},"https://www.cnil.fr/en/ensuring-security-ai-systems-development",[197],"CNIL’s security sheet"," puts Article 32 in plain language: security of processing is a risk-based obligation. European origin does not exempt you from deciding who may change production data. Dust’s buyers often arrive with that question already on the table — which is healthy.",[190,1029,1030,1031,1033],{},"Model choice is a shared strength. Dust lets you pick a model per agent. Nimbus treats that choice as an operating decision: do not use the most expensive model for every small task. See ",[193,1032,426],{"href":45},". The difference is whether the choice sits on an agent you published, or on a step inside a job with a budget in NTUs (work credits).",[190,1035,1036],{},"The fork is practical by role. A team lead who wants reusable helpers on Slack, Notion, and Drive will feel at home in Dust — publishing an agent is the product. An engineer who wants Dust sitting in the middle of existing tools has a path; that is a hub, not a COO login. Finance cares whether a discount field changed, who signed, and which playbook applied. Legal and a DPO in Europe will read CNIL and still ask purpose, retention, and who can write. Ops eventually wants one canvas for a cross-department job, not a catalogue of agents each team invented.",[190,1038,1039],{},"The hidden cost in Dust is operational: who owns the write policy when an agent can change production data. The hidden cost in Nimbus is adoption: operators must run workstreams, not only chat. Pick the cost you can staff.",[221,1041,1043],{"id":1042},"when-dust-is-a-better-fit","When Dust is a better fit",[190,1045,1046],{},"Choose Dust when your job this quarter is “let teams publish reusable agents on our Slack, Notion, and Drive,” you are happy for knowledge to live in those source systems, and you want a flexible studio rather than an opinionated place to finish cross-department work.",[190,1048,1049,1050,1052],{},"Dust is also the better match if you have engineers who want Dust sitting in the middle of your existing tools, and you do not want a workstream-and-record layer yet. It is a strong alternative to ",[193,1051,198],{"href":809}," when you need company context and custom agents you can share — especially in Europe and the mid-market.",[190,1054,1055],{},"Many teams start in an agent studio and later need sign-off, a ledger, and department-shaped work. That is the path Nimbus is built for — not an insult to Dust. You can keep Dust at the edge for engineering-tool agents and put Nimbus on the business jobs that need a sign-off. Coexistence is a policy: Dust agents do not hold production write passwords for money-moving systems; those writes wait in Nimbus.",[221,1057,360],{"id":359},[190,1059,1060],{},"You are not buying a folder of shared agents. You are buying a place go-to-market can draft, finance can review, and the company can still explain the change six months later.",[190,1062,1063,1065],{},[193,1064,383],{"href":51}," are scoped to the workspace and kept read-only until a write is approved. Nimbus publishes 2,000+ integrations; Dust publicly emphasises 70-plus, plus custom developer plug-ins. Count is not the whole story. Dust’s set on Slack, Notion, Drive, GitHub, Salesforce, and Zendesk may be exactly what a studio needs. Nimbus’s catalogue matters when the job spans a longer tail — and when the write path is a release, not an invocation.",[190,1067,399,1068,1071],{},[193,1069,1070],{"href":12},"set this up yourselves",". You do not need vendor engineers sitting with your team for months. Dust’s own rollout guide is still a rollout. Run that if you are buying a studio. Do not wait for it to grow a Lifecycle Graph.",[190,1073,406,1074,409,1076,275],{},[193,1075,39],{"href":40},[193,1077,23],{"href":24},[221,1079,415],{"id":414},[417,1081,1083],{"id":1082},"can-nimbus-replace-dust","Can Nimbus replace Dust?",[190,1085,1086],{},"If Dust is a handful of shared agents on Notion and Slack, yes — you move the jobs into workstreams and the playbooks into the wiki. If you have invested heavily in Dust as a hub for engineering tools, keep Dust at the edge and put Nimbus on the business jobs that need a sign-off.",[417,1088,1090],{"id":1089},"does-nimbus-lock-you-to-one-ai-vendor","Does Nimbus lock you to one AI vendor?",[190,1092,1093,1094,275],{},"No. Both products let you choose models. Dust lets you pick a model per agent. Nimbus treats that choice as an operating decision. See ",[193,1095,426],{"href":45},[417,1097,1099],{"id":1098},"is-dust-more-multiplayer-than-nimbus","Is Dust more “multiplayer” than Nimbus?",[190,1101,1102],{},"Dust coined multiplayer for shared agents, and that is real. Nimbus’s shared surface is the workstream: humans and agent teams across departments on one job, with the Lifecycle Graph as shared memory. Both are multiplayer. Nimbus includes the sign-off and the record.",[417,1104,1106],{"id":1105},"dust-vs-chatgpt-enterprise-vs-nimbus","Dust vs ChatGPT Enterprise vs Nimbus?",[190,1108,1109],{},"Dust is the closer peer: a shared agent studio with connectors. ChatGPT Enterprise is the default assistant plus team-owned agents inside OpenAI’s product. If you are leaving ChatGPT because you need shared, model-choice agents, Dust is the usual next stop. If you are leaving because you need write gates and a ledger, skip the studio. Three products, three centres of gravity: chat, published agent, job.",[417,1111,1113],{"id":1112},"how-should-we-think-about-cost","How should we think about cost?",[190,1115,1116],{},"Dust is typically seats plus usage on a workspace of agents. Nimbus meters the work you run, in NTUs (work credits). Compare a real workload — one programme that updates customer records — not list price per seat. The hidden cost in Dust is operational: who owns the write policy when an agent can change production data. The hidden cost in Nimbus is adoption: operators must run workstreams, not only chat.",[417,1118,1120],{"id":1119},"does-dusts-french-base-make-gdpr-easier","Does Dust’s French base make GDPR easier?",[190,1122,1123],{},"It makes the conversation more natural. CNIL’s guidance still applies: GDPR applies when you develop and run AI that processes personal data, and security of processing is a risk-based obligation. Publishing an agent is not a sign-off on the write.",[417,1125,1127],{"id":1126},"can-we-run-dust-agents-that-draft-and-nimbus-that-releases","Can we run Dust agents that draft and Nimbus that releases?",[190,1129,1130],{},"Yes. Treat Dust as the place teams publish helpers for knowledge work. Feed anything that must change a live system into a Nimbus workstream. Do not let the published agent hold the write password.",[417,1132,1134],{"id":1133},"who-should-own-dust-vs-nimbus","Who should own Dust vs Nimbus?",[190,1136,1137],{},"Platform or IT often owns a studio: who may build, who may run, which models, which connectors. Line operators own Nimbus workstreams because they own the outcome. If engineers want Dust in the middle of developer tools, let them — and keep money-moving writes off that hub.",[221,1139,490],{"id":489},[190,1141,1142,496,1146,500,1148,275],{},[193,1143,1145],{"href":1144},"what-is-multi-agent-ai","What is multi-agent AI",[193,1147,499],{"href":315},[193,1149,810],{"href":809},[221,1151,508],{"id":507},[226,1153,1154,1159,1165,1171],{},[229,1155,1156],{},[193,1157,925],{"href":923,"rel":1158},[197],[229,1160,1161],{},[193,1162,1164],{"href":935,"rel":1163},[197],"Dust rollout guide: Welcome to Dust",[229,1166,1167],{},[193,1168,1170],{"href":1018,"rel":1169},[197],"CNIL, AI system development: recommendations to comply with the GDPR",[229,1172,1173],{},[193,1174,1176],{"href":1024,"rel":1175},[197],"CNIL, Ensuring the security of an AI system's development",{"title":170,"searchDepth":171,"depth":171,"links":1178},[1179,1180,1181,1182,1183,1193,1194],{"id":223,"depth":171,"text":224},{"id":278,"depth":171,"text":279},{"id":1042,"depth":171,"text":1043},{"id":359,"depth":171,"text":360},{"id":414,"depth":171,"text":415,"children":1184},[1185,1186,1187,1188,1189,1190,1191,1192],{"id":1082,"depth":544,"text":1083},{"id":1089,"depth":544,"text":1090},{"id":1098,"depth":544,"text":1099},{"id":1105,"depth":544,"text":1106},{"id":1112,"depth":544,"text":1113},{"id":1119,"depth":544,"text":1120},{"id":1126,"depth":544,"text":1127},{"id":1133,"depth":544,"text":1134},{"id":489,"depth":171,"text":490},{"id":507,"depth":171,"text":508},"Dust is a shared studio for building and publishing AI agents; Nimbus is where departments finish a job with a named signer and a lasting record.","/blog/nimbus-vs-dust",{"title":913,"description":1195},"blog/nimbus-vs-dust",[559,1200,563,1201,1202],"dust","agents","governance","8jfjUGqfgF195ROESiuBDRppv1LMlxIcg2SpS92U-7A",{"id":1205,"title":1206,"archived":164,"authors":165,"badge":1207,"body":1210,"date":555,"definedTerm":165,"department":165,"description":1503,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":164,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":1504,"relatedHeading":165,"seo":1505,"series":559,"sitemap":130,"status":165,"stem":1506,"subhead":165,"tags":1507,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":1511},"content/blog/nimbus-vs-glean.md","Nimbus vs Glean: Finding the Deck vs Running the Job That Deck Implies",{"label":183,"10|authors":1208},[1209],{"name":186,"to":135},{"type":167,"value":1211,"toc":1485},[1212,1220,1227,1235,1237,1284,1286,1301,1308,1311,1314,1317,1320,1323,1327,1334,1337,1340,1343,1345,1348,1363,1368,1374,1376,1380,1386,1390,1393,1397,1400,1404,1407,1411,1418,1422,1433,1435,1438,1442,1445,1447,1458,1460],[190,1213,1214,1219],{},[193,1215,1218],{"href":1216,"rel":1217},"https://www.glean.com/",[197],"Glean"," is workplace search that grew a work assistant on top. It finds files across Drive, Slack, Confluence, and the rest of the workplace — and it respects who is allowed to see them. Nimbus is the place you then run the job those files imply: update the customer record, file the next step, get a person to sign.",[190,1221,1222,1223,1226],{},"Glean’s centre of gravity is ",[232,1224,1225],{},"find the right object, for the right person, at the right time",". Nimbus’s is a signed-off outcome. Both products will say “knowledge” and “agents.” They are not the same purchase. Search that does not leak is a hard, years-long problem. A release on a live system is a different hard problem. Many enterprises have both. They should not pretend one vendor covers both because both say “knowledge graph.”",[190,1228,1229,1234],{},[193,1230,1233],{"href":1231,"rel":1232},"https://www.glean.com/product",[197],"Glean’s product"," connects to Google Workspace, Microsoft 365, Slack, Salesforce, Confluence, Jira, and many more — publicly, 100+ workplace apps — then builds an index that respects the same permissions as the source system. Under the hood that is a mix of classic keyword search and meaning-based search, plus a map of people, documents, and activity. Glean has added assistants and agents so the search layer can also draft and automate. That architecture is why Glean wins large-enterprise search bake-offs. Identity, crawl, and permission fidelity are the hard problems, and Glean has spent years on them.",[221,1236,224],{"id":223},[226,1238,1239,1245,1251,1257,1263,1268,1273,1278],{},[229,1240,1241,1244],{},[232,1242,1243],{},"Workplace search."," An index across the apps the company already uses, so people stop hunting for files.",[229,1246,1247,1250],{},[232,1248,1249],{},"Permission mirroring."," If a document is restricted in Drive, Glean should not surface it in a chat answer. That is the product.",[229,1252,1253,1256],{},[232,1254,1255],{},"Knowledge graph (Glean)."," A map of people, documents, and activity for retrieval. Not the same as Nimbus’s Lifecycle Graph.",[229,1258,1259,1262],{},[232,1260,1261],{},"Crawl."," The programme of connecting apps, mapping identity, and keeping the index fresh. Why IT sponsors Glean. Why it takes time.",[229,1264,1265,1267],{},[232,1266,252],{}," In Nimbus, a shared workspace for one job — not a search result.",[229,1269,1270,1272],{},[232,1271,258],{}," Changing a live system. Search products add agents on top of the index. Nimbus treats the write as a first-class release.",[229,1274,1275,1277],{},[232,1276,264],{}," A causal record of AI work: what ran, who approved it, what changed. Not an index of every file an employee ever touched.",[229,1279,1280,1283],{},[232,1281,1282],{},"Copilot."," Microsoft’s assistant inside Office. Glean searches across many apps, including Microsoft. Neither is a governed execution layer.",[221,1285,279],{"id":278},[190,1287,1288,1289,1294,1295,1300],{},"If you have ever watched a naive chatbot answer from a restricted Drive folder, you understand why Glean exists. Permission mirroring is not a slogan. It is the product: if a document is restricted in Drive, Glean should not surface it in a chat answer. ",[193,1290,1293],{"href":1291,"rel":1292},"https://csrc.nist.gov/pubs/sp/800/53/r5/upd1/final",[197],"NIST SP 800-53 Rev. 5"," Access Control (the AC family) is the control-catalogue reason: the system must enforce who may see what. ",[193,1296,1299],{"href":1297,"rel":1298},"https://www.glean.com/security",[197],"Glean’s security page"," describes that enforcement as a product: permission mirroring, encryption, and compliance claims. Glean is search that does not leak. It is not an AI risk-management framework, and it does not, by itself, put a named signer on a customer-record write.",[190,1302,1303,1304,1307],{},"Glean’s primary object is a document, message, ticket, or person. Nimbus’s primary object is a job, an agent team, a release. Glean’s success metric is time-to-answer. Nimbus’s is time-to-signed-off outcome. Glean’s write path is secondary — agents on top of the index. Nimbus’s write path is first-class: ",[193,1305,1306],{"href":315},"read-only until you open it",", then a person on the change.",[190,1309,1310],{},"Ask whether agents are a feature of search, or search is a feature of agents. Glean is the first. Nimbus is the second. Assistants on a permission-aware index are a reasonable next step for a search company. They still orbit findability. A workstream does not orbit a search result. It orbits a finish line, a budget, and a write policy.",[190,1312,1313],{},"The crawl is why IT sponsors Glean and why it takes time: connecting apps, mapping identity, keeping the index fresh, proving permission QA. That is the right model for a 20,000-person corpus. It is the wrong model if you needed a signed CRM update this quarter and were told to wait until 2019’s files had finished indexing. Nimbus assumes you can already find the policy, or that you will attach the systems this job needs. It does not wait for a company-wide crawl of every historical file.",[190,1315,1316],{},"The two “graphs” are the usual confusion. Glean’s knowledge graph is mostly an index of people and content for retrieval. Nimbus’s Lifecycle Graph is an operational ledger of work, agents, and releases. Collapsing the terms in a vendor meeting is how you buy the wrong one. You can run both graphs. You cannot substitute one for the other.",[190,1318,1319],{},"Role by role, the fork is practical. A CIO running a knowledge programme wants a universal search bar across 100+ apps, with permission mirroring as the non-negotiable. That is Glean. A Head of RevOps wants an agent to propose opportunity updates with a named signer — search will find the deck; it will not be the release. Security cares that Glean does not leak restricted files, and still cares who may change Salesforce. Knowledge workers want time-to-answer. Operators want time-to-signed-off outcome. Legal will not accept “the assistant found it” as the story of why a customer field moved.",[190,1321,1322],{},"A healthy split: Glean for findability across the sprawling workplace; Nimbus for execution on the jobs that mutate systems of record. Do not stretch Glean into an operating layer because it added agents. Do not stretch Nimbus into a crawl of every Confluence page because Perception can answer questions about the record.",[221,1324,1326],{"id":1325},"when-glean-is-a-better-fit","When Glean is a better fit",[190,1328,1329,1330,1333],{},"Choose Glean when the corpus is huge, permissions ",[204,1331,1332],{},"are"," the product, and you need a universal search bar across 100+ apps before you invent agent teams. Choose Glean also if the executive sponsor is the CIO’s knowledge programme rather than a line-of-business operating model.",[190,1335,1336],{},"Deployment is a crawl programme: identity mapping, permission QA, often with Glean or partner engineers in the building. That is the right model for a 20,000-person corpus. Do not treat that implementation cost as a reason Glean is “worse.” It is the cost of doing permission-aware search well.",[190,1338,1339],{},"Do not choose Glean as a stealth agent operating layer. You will spend a year on crawl quality and still lack workstreams, specialist teams, and change control on writes.",[190,1341,1342],{},"Some organisations will run Glean for findability and Nimbus for execution. That is a coherent architecture if you do not pretend one graph is the other. Keep Glean as the place people find the deck. Put the job the deck implies — update the customer record, file the next step, get a person to sign — in a Nimbus workstream. Connectors in Nimbus are not a substitute for Glean-scale historical crawl. A Glean assistant is not a substitute for a quoted write.",[221,1344,360],{"id":359},[190,1346,1347],{},"Search exists inside Nimbus as a way to ask about the record, your playbooks, and the systems you attached. It is not a company-wide crawl of 2019.",[190,1349,1350,1351,1353,1354,1356,1357,1359,1360,1362],{},"The ",[193,1352,379],{"href":28}," is what the company asserts. ",[193,1355,383],{"href":51}," are scoped per ",[193,1358,673],{"href":32},". Agents do not get “search everything this user could theoretically open” as the default tool. They get the systems you attached, in the mode you allowed (usually read), until a human releases a write. ",[193,1361,395],{"href":36}," is ordinary language over that scoped world, not a second Glean.",[190,1364,399,1365,1367],{},[193,1366,402],{"href":12},": a workspace, wiki, connectors, a first workstream. You do not wait for an index of every historical file to finish.",[190,1369,406,1370,409,1372,275],{},[193,1371,39],{"href":40},[193,1373,23],{"href":24},[221,1375,415],{"id":414},[417,1377,1379],{"id":1378},"does-glean-require-more-implementation-than-nimbus","Does Glean require more implementation than Nimbus?",[190,1381,1382,1383,1385],{},"Usually yes. Permission-aware crawl at enterprise scale is a programme. Nimbus is self-service for most buyers: you are not waiting on vendor engineers sitting with your team for months to get collaboration, sign-off, and a causal record. That is not a claim that Glean is slow for no reason. Crawl and permission QA ",[204,1384,1332],{}," the work.",[417,1387,1389],{"id":1388},"does-nimbus-replace-glean","Does Nimbus replace Glean?",[190,1391,1392],{},"Only if your Glean usage is a thin Q&A bot on a small corpus. It does not replace Glean as permission-aware enterprise search across a sprawling workplace. If you need the latter, keep a search product.",[417,1394,1396],{"id":1395},"both-mention-knowledge-graphs-are-they-the-same","Both mention knowledge graphs. Are they the same?",[190,1398,1399],{},"No. Glean’s graph is mostly an index of people and content for retrieval. Nimbus’s Lifecycle Graph is an operational ledger of work, agents, and releases. Collapsing the terms in a vendor meeting is how you buy the wrong one.",[417,1401,1403],{"id":1402},"can-nimbus-search-drive-and-slack","Can Nimbus search Drive and Slack?",[190,1405,1406],{},"Connectors bring live systems into agent context and into questions you ask about the record. That is targeted operational retrieval, not a Glean-scale crawl of every historical file. If you need the latter, keep a search product.",[417,1408,1410],{"id":1409},"glean-vs-copilot-vs-nimbus","Glean vs Copilot vs Nimbus?",[190,1412,1413,1414,275],{},"Copilot is productivity inside Microsoft that respects Microsoft permissions. Glean is search across many apps (including Microsoft) that respects source permissions. Nimbus is governed execution. A Microsoft-first company may still need Glean if SharePoint search is not enough, and may still need Nimbus if Copilot Studio is not an operating layer. See ",[193,1415,1417],{"href":1416},"nimbus-vs-microsoft-copilot","Nimbus vs Microsoft Copilot",[417,1419,1421],{"id":1420},"can-we-run-glean-and-nimbus-together","Can we run Glean and Nimbus together?",[190,1423,1424,1425,1428,1429,1432],{},"Yes. That is the intended coexistence for organisations that have both a findability problem and an execution problem. Do not give Glean agents production write credentials because the index is permission-aware. Permission to ",[204,1426,1427],{},"see"," is not permission to ",[204,1430,1431],{},"change",". Route mutations through Nimbus governance.",[417,1434,476],{"id":475},[190,1436,1437],{},"The CIO’s knowledge programme typically owns Glean: identity mapping, crawl, permission QA. Line operators own Nimbus workstreams because they own the systems of record those jobs touch. Security reviews both — leak prevention on the search side, write gates on the execution side.",[417,1439,1441],{"id":1440},"if-glean-has-agents-now-why-add-nimbus","If Glean has agents now, why add Nimbus?",[190,1443,1444],{},"Because agents on an index are still a feature of search. Time-to-answer is not time-to-signed-off outcome. If the job is to change a customer record with a person on the write, you need a workstream, a wiki clause, and a graph — not another way to find the deck.",[221,1446,490],{"id":489},[190,1448,1449,496,1453,500,1456,275],{},[193,1450,1452],{"href":1451},"what-is-enterprise-rag","What is enterprise RAG",[193,1454,1455],{"href":391},"What is a lifecycle graph",[193,1457,1417],{"href":1416},[221,1459,508],{"id":507},[226,1461,1462,1467,1473,1479],{},[229,1463,1464],{},[193,1465,1218],{"href":1216,"rel":1466},[197],[229,1468,1469],{},[193,1470,1472],{"href":1231,"rel":1471},[197],"Glean product",[229,1474,1475],{},[193,1476,1478],{"href":1297,"rel":1477},[197],"Glean security",[229,1480,1481],{},[193,1482,1484],{"href":1291,"rel":1483},[197],"NIST SP 800-53 Rev. 5 (Access Control)",{"title":170,"searchDepth":171,"depth":171,"links":1486},[1487,1488,1489,1490,1491,1501,1502],{"id":223,"depth":171,"text":224},{"id":278,"depth":171,"text":279},{"id":1325,"depth":171,"text":1326},{"id":359,"depth":171,"text":360},{"id":414,"depth":171,"text":415,"children":1492},[1493,1494,1495,1496,1497,1498,1499,1500],{"id":1378,"depth":544,"text":1379},{"id":1388,"depth":544,"text":1389},{"id":1395,"depth":544,"text":1396},{"id":1402,"depth":544,"text":1403},{"id":1409,"depth":544,"text":1410},{"id":1420,"depth":544,"text":1421},{"id":475,"depth":544,"text":476},{"id":1440,"depth":544,"text":1441},{"id":489,"depth":171,"text":490},{"id":507,"depth":171,"text":508},"Glean is permission-aware workplace search; Nimbus is the place an agent can change a customer record — with a person signing off.","/blog/nimbus-vs-glean",{"title":1206,"description":1503},"blog/nimbus-vs-glean",[559,1508,1509,1510,1201],"glean","enterprise-search","knowledge-graph","lopHySQjEaMS7w53g7VN72jOHjcGsrF3qHReS1qcl0Q",{"id":1513,"title":1514,"archived":164,"authors":165,"badge":1515,"body":1518,"date":555,"definedTerm":165,"department":165,"description":1817,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":164,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":1818,"relatedHeading":165,"seo":1819,"series":559,"sitemap":130,"status":165,"stem":1820,"subhead":165,"tags":1821,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":1826},"content/blog/nimbus-vs-hermes.md","Nimbus vs Hermes: A Personal Agent That Learns You, or a System That Remembers the Business?",{"label":183,"10|authors":1516},[1517],{"name":186,"to":135},{"type":167,"value":1519,"toc":1799},[1520,1536,1539,1554,1556,1612,1614,1622,1625,1634,1640,1643,1655,1661,1665,1671,1676,1679,1681,1684,1695,1701,1703,1707,1710,1714,1717,1721,1724,1728,1731,1735,1738,1742,1748,1752,1755,1759,1762,1764,1773,1775],[190,1521,1522,1527,1528,1531,1532,1535],{},[193,1523,1526],{"href":1524,"rel":1525},"https://hermes-agent.nousresearch.com/",[197],"Hermes Agent"," is built to get better at ",[204,1529,1530],{},"you",". It remembers your projects, writes little how-to notes for itself after a hard task, and can schedule briefings while you are away. Nimbus is built so the ",[204,1533,1534],{},"business"," still knows what happened when that person is on a plane: official playbooks, a named signer on writes, and a record that does not live on one laptop.",[190,1537,1538],{},"Both are “an agent that remembers.” They are not the same memory. Personal memory is preferences, procedures, the way you like a report. Company memory is playbooks, signers, and a graph the next person can query. Hermes is honest about the bargain: remembering you is the product. Nimbus is honest about a different bargain: the company still knows after you leave.",[190,1540,1541,1542,1547,1548,1553],{},"Hermes is a real step beyond a chat window that forgets you every morning. It is an open-source personal agent from ",[193,1543,1546],{"href":1544,"rel":1545},"https://nousresearch.com/",[197],"Nous Research",". You install it on a Mac, Windows, or Linux machine. It can also live in Telegram, Discord, Slack, WhatsApp, Signal, email, or a terminal. It talks to many model providers, so you are not locked to one lab. It can spin up helper agents with their own conversations. The ",[193,1549,1552],{"href":1550,"rel":1551},"https://github.com/nousresearch/hermes-agent/",[197],"code"," is public. If you are a founder, a researcher, or a power user who will actually look after the install, Hermes is doing the job it was designed for.",[221,1555,224],{"id":223},[226,1557,1558,1568,1574,1580,1585,1590,1595,1600],{},[229,1559,1560,1563,1564,1567],{},[232,1561,1562],{},"Hermes Agent."," An open-source personal agent from ",[193,1565,1546],{"href":1544,"rel":1566},[197],". You install it on a Mac, Windows, or Linux machine. It can also live in Telegram, Discord, Slack, WhatsApp, Signal, email, or a terminal.",[229,1569,1570,1573],{},[232,1571,1572],{},"Self-hosted."," You run the software. You pay the model bill. You keep the secrets. You are the operator.",[229,1575,1576,1579],{},[232,1577,1578],{},"Personal memory."," Preferences, procedures, the way you like a report. Powerful for one operator. Risky if that operator also has mailbox and company-file access.",[229,1581,1582,1584],{},[232,1583,252],{}," In Nimbus, a shared workspace for one job — not a private conversation on a machine.",[229,1586,1587,1589],{},[232,1588,636],{}," Official playbooks: how we book a journal, who may sign, what “done” means. Agents read that, not a private note on a desktop.",[229,1591,1592,1594],{},[232,1593,258],{}," Changing a live system. Reads are on by default. Writes stay off until you name a person who must approve.",[229,1596,1597,1599],{},[232,1598,264],{}," The company record of what ran, who approved, and what changed. When the operator leaves, the record does not leave with their laptop.",[229,1601,1602,1605,1606,1611],{},[232,1603,1604],{},"Secure by Design."," ",[193,1607,1610],{"href":1608,"rel":1609},"https://www.cisa.gov/securebydesign",[197],"CISA’s programme"," about who owns security outcomes. When you run software yourself, you are the operator.",[221,1613,279],{"id":278},[190,1615,1616,1617,1621],{},"You also own the upkeep. A laptop agent with mailbox and company files is a privileged identity you operate. ",[193,1618,1620],{"href":1608,"rel":1619},[197],"CISA’s Secure by Design"," framing is blunt: if you chose to run the agent yourself, you own the outcome. Logging, least privilege, and a named signer are yours to provide. Hermes will not invent them because it learned your email voice.",[190,1623,1624],{},"On Hermes, the trail of a finance journal is a conversation on a machine, a how-to note the agent wrote for itself, maybe an email it sent. That may be enough for one person. It is not enough for an auditor who asks, “Show me the approved version.” Self-hosting means you keep the secrets and pay the model bill. It does not mean the company has a release process. Hosting choice is not company governance.",[190,1626,1627,1628,1630,1631,1633],{},"On Nimbus, finance opens a ",[193,1629,673],{"href":373},". The wiki states the journal policy. The ledger connector is read-only until a human releases the write. The ",[193,1632,23],{"href":391}," keeps the brief, the draft, the signer, and the change. When the operator leaves, the record does not leave with their laptop. Nimbus is not trying to learn your email voice. It is trying to make sure finance cannot post a journal without a named signer, and that the analysis still exists in two years.",[190,1635,1636,1637,1639],{},"If three people each run Hermes, you have three memories and no shared playbook. One of them will eventually put a production password in a local file “just for this week.” That is not a Hermes flaw. It is what happens when a personal agent becomes the unofficial company system — ",[193,1638,331],{"href":330}," with a better memory. Auto-promoting a note from one user’s Hermes into company-wide write access is how a friendly shortcut spreads.",[190,1641,1642],{},"A laptop is convenient and easy to lose. A server you run yourself is always on and a bigger target if it is reachable from the internet. Neither gives you a named signer on a journal. Hermes can live in many chat apps; reach is not a control system. The more surfaces the agent sits on, the more ways a privileged identity can be messaged.",[190,1644,1645,1646,1649,1650,1654],{},"Role by role: a founder or researcher who will patch the install gets a personal agent that improves at ",[204,1647,1648],{},"their"," workflows — that is the fit. IT should not be asked to standardise the company on a fleet of laptops and a spreadsheet of who is supposed to update them. Finance cannot treat a how-to note on a desktop as the journal policy. Security inherits CISA’s point: you ran it, you own the outcome. A COO who needs an org chart for those personal agents is already in a different product — see ",[193,1651,1653],{"href":1652},"nimbus-vs-paperclip","Nimbus vs Paperclip",". Operators who need the business to remember should not wait for each person’s Hermes to become unofficial infrastructure.",[190,1656,1657,1658,1660],{},"The job split is clean if you keep it clean. Hermes (or something like ",[193,1659,710],{"href":709},") as a personal assistant with no production passwords. Nimbus as the place that work is submitted, approved, and remembered. Feed drafts into a workstream the way you would feed a human’s first pass. Do not let Hermes hold the write password.",[221,1662,1664],{"id":1663},"when-hermes-is-a-better-fit","When Hermes is a better fit",[190,1666,1667,1668,1670],{},"Choose Hermes when you are the user, you want an agent that improves at ",[204,1669,301],{}," workflows, and the blast radius is your own files. Choose it to feel what a persistent agent is like before you operationalise anything. Choose it in a lab that will never touch customer systems.",[190,1672,1673,1674,275],{},"Do not standardise the company on Hermes and call it an AI programme. You will recreate a pile of personal agents and a spreadsheet of who is supposed to patch them. If you need an org chart for those agents, that is a different product again — see ",[193,1675,1653],{"href":1652},[190,1677,1678],{},"You can use both. Hermes as a personal assistant with no production passwords. Nimbus as the place that work is submitted, approved, and remembered. That coexistence only works if credentials stay out of the personal agent. A brilliant personal memory with a production login is still a privileged identity on a laptop.",[221,1680,360],{"id":359},[190,1682,1683],{},"Nimbus is a company system, not a program you install on one person’s machine. You log in the way you log into any other business app. You do not hope they remember to patch it.",[190,1685,1686,1688,1689,1691,1692,1694],{},[193,1687,383],{"href":51}," link to the tools you already run — the ledger, the CRM, the shared drive. ",[193,1690,39],{"href":40}," is the release path: agents draft, humans release, the graph keeps the decision. The ",[193,1693,379],{"href":28}," is where “how we do this” lives after a human has reviewed it — not a private note the agent wrote for itself. You still review the vendor. You do not become the platform team for every laptop.",[190,1696,1697,1698,275],{},"Start at the ",[193,1699,1700],{"href":12},"overview",[221,1702,415],{"id":414},[417,1704,1706],{"id":1705},"is-nimbus-built-on-hermes","Is Nimbus built on Hermes?",[190,1708,1709],{},"No. They sit on different layers. Nimbus may call some of the same models Hermes uses. That is the model market, not a fork.",[417,1711,1713],{"id":1712},"can-hermes-be-our-company-ai-platform","Can Hermes be our company AI platform?",[190,1715,1716],{},"Only if you are willing to staff the upkeep: identity, secrets, updates, and a release process for anything that touches production. At that point you are building a company system by hand. Most operators should not.",[417,1718,1720],{"id":1719},"where-should-the-how-we-do-this-notes-live","Where should the “how we do this” notes live?",[190,1722,1723],{},"On a personal agent, or as playbooks in the Nimbus wiki after a human has reviewed them. Auto-promoting a note from one user’s Hermes into company-wide write access is how a friendly shortcut spreads.",[417,1725,1727],{"id":1726},"can-we-run-hermes-beside-nimbus","Can we run Hermes beside Nimbus?",[190,1729,1730],{},"Yes — as a personal assistant with no production credentials. Feed drafts into a Nimbus workstream the way you would feed a human’s first pass. Do not let Hermes hold the write password.",[417,1732,1734],{"id":1733},"does-it-matter-if-hermes-runs-on-a-laptop-or-a-server","Does it matter if Hermes runs on a laptop or a server?",[190,1736,1737],{},"A laptop is convenient and easy to lose. A server you run yourself is always on and a bigger target if it is reachable from the internet. Neither gives you a named signer on a journal. Hosting choice is not company governance.",[417,1739,1741],{"id":1740},"how-is-hermes-different-from-openclaw","How is Hermes different from OpenClaw?",[190,1743,1744,1745,275],{},"Same layer — a personal assistant you look after — different emphasis. OpenClaw maximises channels. Hermes maximises skills and personal memory. Neither is a company OS. See ",[193,1746,1747],{"href":709},"Nimbus vs OpenClaw",[417,1749,1751],{"id":1750},"who-owns-security-if-we-allow-hermes","Who owns security if we allow Hermes?",[190,1753,1754],{},"You do. CISA’s Secure by Design framing is about who owns security outcomes. When you run the software yourself, you are the operator. Logging, least privilege, and a named signer are yours to provide. Nimbus does not remove the need to review a vendor; it does mean you are not the platform team for every laptop.",[417,1756,1758],{"id":1757},"what-happens-when-the-person-who-ran-hermes-leaves","What happens when the person who ran Hermes leaves?",[190,1760,1761],{},"Their personal memory leaves with them, unless you copied it somewhere else. That is the product working as designed. If the business needed the journal policy, the signer, and the change, those should already have lived in a workstream and a graph — not on a machine that is about to be wiped.",[221,1763,490],{"id":489},[190,1765,1766,496,1769,500,1771,275],{},[193,1767,1768],{"href":702},"What is institutional memory in enterprise AI",[193,1770,499],{"href":315},[193,1772,1747],{"href":709},[221,1774,508],{"id":507},[226,1776,1777,1782,1788,1793],{},[229,1778,1779],{},[193,1780,1526],{"href":1524,"rel":1781},[197],[229,1783,1784],{},[193,1785,1787],{"href":1550,"rel":1786},[197],"Hermes Agent on GitHub",[229,1789,1790],{},[193,1791,1546],{"href":1544,"rel":1792},[197],[229,1794,1795],{},[193,1796,1798],{"href":1608,"rel":1797},[197],"CISA Secure by Design",{"title":170,"searchDepth":171,"depth":171,"links":1800},[1801,1802,1803,1804,1805,1815,1816],{"id":223,"depth":171,"text":224},{"id":278,"depth":171,"text":279},{"id":1663,"depth":171,"text":1664},{"id":359,"depth":171,"text":360},{"id":414,"depth":171,"text":415,"children":1806},[1807,1808,1809,1810,1811,1812,1813,1814],{"id":1705,"depth":544,"text":1706},{"id":1712,"depth":544,"text":1713},{"id":1719,"depth":544,"text":1720},{"id":1726,"depth":544,"text":1727},{"id":1733,"depth":544,"text":1734},{"id":1740,"depth":544,"text":1741},{"id":1750,"depth":544,"text":1751},{"id":1757,"depth":544,"text":1758},{"id":489,"depth":171,"text":490},{"id":507,"depth":171,"text":508},"Hermes Agent is a self-hosted personal agent that learns how you work; Nimbus remembers how the company works when that person is away.","/blog/nimbus-vs-hermes",{"title":1514,"description":1817},"blog/nimbus-vs-hermes",[559,1822,1823,1824,1825],"hermes","nous-research","open-source-agents","memory","6l33KTk6TYiOpXPTJL9a4rony4Mmvo6cSklzRnN_rcs",{"id":1828,"title":1829,"archived":164,"authors":165,"badge":1830,"body":1833,"date":555,"definedTerm":165,"department":165,"description":2147,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":164,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":2148,"relatedHeading":165,"seo":2149,"series":559,"sitemap":130,"status":165,"stem":2150,"subhead":165,"tags":2151,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":2155},"content/blog/nimbus-vs-microsoft-copilot.md","Nimbus vs Microsoft Copilot: Great Inside Office, or Work That Leaves Microsoft?",{"label":183,"10|authors":1831},[1832],{"name":186,"to":135},{"type":167,"value":1834,"toc":2129},[1835,1854,1857,1880,1882,1933,1935,1941,1950,1956,1966,1969,1972,1976,1979,1982,1985,1988,1991,1993,2002,2012,2017,2021,2023,2027,2030,2034,2037,2041,2046,2050,2057,2061,2064,2068,2071,2073,2080,2084,2090,2092,2102,2104],[190,1836,1837,1838,1845,1846,1853],{},"“Copilot” is several products that get collapsed in procurement. ",[232,1839,1840],{},[193,1841,1844],{"href":1842,"rel":1843},"https://www.microsoft.com/microsoft-365/copilot",[197],"Microsoft 365 Copilot"," is the add-on that sits in Word, Excel, PowerPoint, Outlook, Teams, and the Copilot app. ",[232,1847,1848],{},[193,1849,1852],{"href":1850,"rel":1851},"https://learn.microsoft.com/en-us/microsoft-copilot-studio/",[197],"Copilot Studio"," is the low-code environment for multi-step agents beyond Microsoft. Nimbus is for work that leaves Microsoft — Salesforce, NetSuite, and the rest of the stack where money actually moves.",[190,1855,1856],{},"Nobody else will be as good at “summarise this thread and the attached deck” inside Outlook. That recap is tenant productivity. Updating forty opportunities in Salesforce is company operations. If your programme starts with “every knowledge worker has a Copilot licence,” you are specifying Microsoft. If it starts with “RevOps will not allow unapproved Salesforce writes from an agent, and we need a record of those releases,” you are specifying Nimbus. You can keep both. Using Nimbus does not mean ripping Copilot out of Office.",[190,1858,1859,1860,1865,1866,1871,1872,1875,1876,1879],{},"Microsoft’s own ",[193,1861,1864],{"href":1862,"rel":1863},"https://learn.microsoft.com/en-us/microsoft-365/copilot/microsoft-365-copilot-architecture",[197],"architecture"," and ",[193,1867,1870],{"href":1868,"rel":1869},"https://learn.microsoft.com/en-us/copilot/microsoft-365/microsoft-365-copilot-privacy",[197],"privacy"," docs are the source: Copilot is grounded in Microsoft Graph — mail, files, meetings, and sites the user can already access — and prompts, responses, and Graph data are not used to train foundation LLMs. That is the right privacy story for find-and-draft inside Microsoft. It still describes ",[204,1873,1874],{},"find and draft inside Microsoft",", not ",[204,1877,1878],{},"sign a write in Salesforce",". Agent Builder covers simple agents inside Copilot, grounded in Microsoft 365 content, for information workers. Studio is the step that leaves Graph.",[221,1881,224],{"id":223},[226,1883,1884,1890,1896,1902,1908,1913,1922,1927],{},[229,1885,1886,1889],{},[232,1887,1888],{},"Microsoft 365 Copilot."," The per-person assistant inside Office, grounded in Microsoft Graph — mail, files, meetings, and sites the user can already access.",[229,1891,1892,1895],{},[232,1893,1894],{},"Microsoft Graph."," The map of what this person can already open in Microsoft 365. Copilot should not leak a file they cannot open in SharePoint.",[229,1897,1898,1901],{},[232,1899,1900],{},"Copilot Studio."," Low-code agents with branching, approvals, and connectors to Salesforce, SAP, ServiceNow, and custom APIs. You can publish to Teams. Metering is often credits or messages on top of licences.",[229,1903,1904,1907],{},[232,1905,1906],{},"Agent Builder."," Simple agents inside Copilot, grounded in Microsoft 365 content, for information workers.",[229,1909,1910,1912],{},[232,1911,252],{}," In Nimbus, a shared workspace for one job across systems that are not all Microsoft.",[229,1914,1915,1917,1918,1921],{},[232,1916,258],{}," Changing a live system. You ",[204,1919,1920],{},"can"," update Salesforce from Studio. The update is a flow-shaped side effect in Microsoft’s world. In Nimbus it is a quoted release with a named signer.",[229,1923,1924,1926],{},[232,1925,264],{}," The causal record of who approved, what changed, and what the next team should believe.",[229,1928,1929,1932],{},[232,1930,1931],{},"E5."," Microsoft 365 E5 explains identity, compliance, and Office. It does not explain CRM write-back or a company work ledger.",[221,1934,279],{"id":278},[190,1936,1937,1938,1940],{},"Studio agents that leave Graph for other connectors inherit a different permission story: connector logins, rules that stop sensitive files leaking, environment strategy. IT knows this is where Copilot programmes stall. You ",[204,1939,1920],{}," update Salesforce from Studio. The update is a flow-shaped side effect in Microsoft’s world. In Nimbus it is a quoted release with a named signer. Approvals in a Power Platform artefact are real. They are not a Lifecycle Graph of the job across departments.",[190,1942,1943,1944,1946,1947,1949],{},"In Nimbus, the scarce resource is control of work across systems that are not all Microsoft. The quarterly review deck may live in SharePoint. The opportunities live in Salesforce. The revenue number finance trusts may live in NetSuite. A ",[193,1945,673],{"href":373}," puts those in one job. Records stay read-only until someone who is allowed to approve writes actually does. The ",[193,1948,23],{"href":391}," keeps the release.",[190,1951,1952,1955],{},[193,1953,1218],{"href":1954},"nimbus-vs-glean","-class search and Copilot-class Graph grounding solve findability. Nimbus assumes you can already find the policy. The failure is that AI work does not land in a signed-off artefact. Purpose limitation is easier to explain when a recruiting workstream cannot see finance forecasts. A Copilot licence that sees “whatever this user can already open” is a different design — Microsoft’s Graph design, by intention. That design is correct inside Office. It is a wide blast radius if the same licence is treated as the operating model for every system the user can already open.",[190,1957,1958,1959,1961,1962,1965],{},"Lock-in is the honest trade. Copilot deepens Microsoft 365. Nimbus is lock-in of a different kind: the work loop and the graph. If most proprietary work is already in Microsoft, Copilot’s return is easier. If most money-moving systems are Salesforce, NetSuite, and specialist software, Copilot Studio becomes a connector project — and Nimbus was designed as that project plus the record. E5 explains identity, compliance, and Office. It does not explain CRM ",[193,1960,695],{"href":315},", choosing models across vendors, or a Lifecycle Graph. Standardise Copilot where Microsoft’s graph ",[204,1963,1964],{},"is"," the work. Standardise an operating layer where the business process is the work.",[190,1967,1968],{},"Role by role: a knowledge worker in Word, Excel, Outlook, and Teams wants the side pane — nobody else will recap the thread and the attached deck as well. IT owns Graph, licences, and often Studio as a Power Platform artefact: a helpdesk bot, an HR FAQ, a Teams helper. RevOps lives in Salesforce, not in SharePoint; a Studio connector to Salesforce is a flow-shaped side effect, not a company release. Finance trusts NetSuite, not the recap. Security will like Graph grounding and the privacy docs, and still ask who signed a CRM write. A CIO who already bought E5 should use Copilot where Microsoft’s graph is the work — and still not pretend E5 bought an operating layer.",[190,1970,1971],{},"SharePoint agents are Q&A on sites. Use them for findability. Do not use them as the operating model. Keep Copilot in Office. Put the job that leaves Microsoft in a workstream.",[221,1973,1975],{"id":1974},"when-microsoft-copilot-is-a-better-fit","When Microsoft Copilot is a better fit",[190,1977,1978],{},"Choose Microsoft 365 Copilot when the job is knowledge-worker productivity in Word, Excel, Outlook, and Teams, and Microsoft’s own files and mail are the corpus.",[190,1980,1981],{},"Choose Copilot Studio when the agent is a Power Platform artefact IT will own — a helpdesk bot, an HR FAQ, a Teams helper. Metering is often credits or messages on top of licences; budget that as a Microsoft programme, not as a Nimbus substitute.",[190,1983,1984],{},"SharePoint agents are Q&A on sites. Use them for findability. Do not use them as the operating model.",[190,1986,1987],{},"Do not choose Copilot as a stealth operating layer for non-Microsoft systems. You will spend a year on connector reviews and still lack workstreams, specialist teams, and a Lifecycle Graph.",[190,1989,1990],{},"Keep Copilot in Office. Using Nimbus does not mean ripping it out. A coherent coexistence: Copilot for tenant productivity; Nimbus for jobs that also touch Salesforce, NetSuite, and the rest of the stack. Drafts can move from a recap into a workstream. Write credentials for money-moving systems should sit in Nimbus connector scopes, not in a Studio flow by default.",[221,1992,360],{"id":359},[190,1994,1995,1996,1998,1999,2001],{},"Nimbus does not try to be the Word side pane. It does not assume the only intelligence in the company is whatever Microsoft licensed this quarter. See ",[193,1997,426],{"href":45},". Routing includes not throwing the most powerful model at a simple lookup. Treat Microsoft-hosted models as infrastructure options in an enterprise conversation with ",[193,2000,788],{"href":99},", not as a reason Copilot and Nimbus are the same product.",[190,2003,1350,2004,1353,2006,2008,2009,2011],{},[193,2005,379],{"href":28},[193,2007,383],{"href":51}," are scoped per workspace. Agents get the systems you attached, in the mode you allowed, until a human releases a write. ",[193,2010,387],{"href":20}," finish the work Copilot handed you after the recap.",[190,2013,399,2014,2016],{},[193,2015,402],{"href":12},". Copilot programmes at organisational scale are famous for implementation. Keep Copilot in Office; do not staff a consulting partner to invent an operating layer.",[190,2018,406,2019,275],{},[193,2020,39],{"href":40},[221,2022,415],{"id":414},[417,2024,2026],{"id":2025},"does-nimbus-replace-microsoft-365-copilot","Does Nimbus replace Microsoft 365 Copilot?",[190,2028,2029],{},"No. Keep Copilot in Office. Nimbus does not try to be the Word side pane. It tries to be the place agent teams finish work that leaves Microsoft.",[417,2031,2033],{"id":2032},"does-copilot-studio-replace-nimbus","Does Copilot Studio replace Nimbus?",[190,2035,2036],{},"Only if “a few Power Platform agents” is the entire AI programme. Studio can be shared inside the Microsoft tenant. It does not replace Nimbus as a governed execution layer with a company wiki and an operational ledger.",[417,2038,2040],{"id":2039},"can-nimbus-use-azure-openai-or-microsoft-models","Can Nimbus use Azure OpenAI or Microsoft models?",[190,2042,2043,2044,2001],{},"Nimbus routes models for quality, cost, and latency — including not throwing the most powerful model at a simple lookup. Treat Microsoft-hosted models as infrastructure options in an enterprise conversation with ",[193,2045,788],{"href":99},[417,2047,2049],{"id":2048},"why-not-standardise-on-copilot-because-we-already-buy-microsoft-365-e5","Why not standardise on Copilot because we already buy Microsoft 365 E5?",[190,2051,2052,2053,1961,2055,1965],{},"E5 explains identity, compliance, and Office. It does not explain CRM ",[193,2054,695],{"href":315},[204,2056,1964],{},[417,2058,2060],{"id":2059},"do-we-need-a-microsoft-partner-to-get-nimbus-running","Do we need a Microsoft partner to get Nimbus running?",[190,2062,2063],{},"No. You can set it up yourselves. Copilot Studio at organisational scale usually is not self-serve in the same way.",[417,2065,2067],{"id":2066},"can-we-keep-copilot-and-put-salesforce-writes-in-nimbus","Can we keep Copilot and put Salesforce writes in Nimbus?",[190,2069,2070],{},"Yes. That is the intended coexistence. Recap in Outlook; finish in a workstream. Do not let a Studio Salesforce connector become the unofficial write path “because we already had an approval step in the flow.” Quote the change, name the signer, store the outcome.",[417,2072,476],{"id":475},[190,2074,2075,2076,2079],{},"IT typically owns Microsoft 365 Copilot and Studio: licences, Graph, Power Platform environments. Line operators own Nimbus workstreams that touch Salesforce, NetSuite, and specialist systems. Security reviews Graph grounding ",[204,2077,2078],{},"and"," write gates. A single “we already pay Microsoft” owner will stretch Copilot into an operating layer.",[417,2081,2083],{"id":2082},"what-about-glean-if-we-already-have-copilot","What about Glean if we already have Copilot?",[190,2085,2086,2087,275],{},"Copilot respects Microsoft permissions inside Microsoft. Glean searches across many apps, including Microsoft, and respects source permissions. You may still need Glean if SharePoint search is not enough, and still need Nimbus if neither is an operating layer. See ",[193,2088,2089],{"href":1954},"Nimbus vs Glean",[221,2091,490],{"id":489},[190,2093,2094,496,2096,500,2100,275],{},[193,2095,499],{"href":315},[193,2097,2099],{"href":2098},"what-is-an-enterprise-ai-operating-system","What is an enterprise AI operating system",[193,2101,2089],{"href":1954},[221,2103,508],{"id":507},[226,2105,2106,2111,2117,2123],{},[229,2107,2108],{},[193,2109,1844],{"href":1842,"rel":2110},[197],[229,2112,2113],{},[193,2114,2116],{"href":1868,"rel":2115},[197],"Microsoft 365 Copilot privacy",[229,2118,2119],{},[193,2120,2122],{"href":1862,"rel":2121},[197],"Microsoft 365 Copilot architecture",[229,2124,2125],{},[193,2126,2128],{"href":1850,"rel":2127},[197],"Microsoft Copilot Studio",{"title":170,"searchDepth":171,"depth":171,"links":2130},[2131,2132,2133,2134,2135,2145,2146],{"id":223,"depth":171,"text":224},{"id":278,"depth":171,"text":279},{"id":1974,"depth":171,"text":1975},{"id":359,"depth":171,"text":360},{"id":414,"depth":171,"text":415,"children":2136},[2137,2138,2139,2140,2141,2142,2143,2144],{"id":2025,"depth":544,"text":2026},{"id":2032,"depth":544,"text":2033},{"id":2039,"depth":544,"text":2040},{"id":2048,"depth":544,"text":2049},{"id":2059,"depth":544,"text":2060},{"id":2066,"depth":544,"text":2067},{"id":475,"depth":544,"text":476},{"id":2082,"depth":544,"text":2083},{"id":489,"depth":171,"text":490},{"id":507,"depth":171,"text":508},"Microsoft 365 Copilot lives in Word, Outlook, and Teams; Nimbus is for jobs that also touch Salesforce, NetSuite, and the rest of the business.","/blog/nimbus-vs-microsoft-copilot",{"title":1829,"description":2147},"blog/nimbus-vs-microsoft-copilot",[559,2152,2153,2154,563],"microsoft-copilot","copilot-studio","m365","7yJ3KRBR_5jku0p8MFGnMWx_1IEoNXkcwyiCtkzc7d0",{"id":2157,"title":2158,"archived":164,"authors":165,"badge":2159,"body":2162,"date":555,"definedTerm":165,"department":165,"description":2436,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":164,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":2437,"relatedHeading":165,"seo":2438,"series":559,"sitemap":130,"status":165,"stem":2439,"subhead":165,"tags":2440,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":2444},"content/blog/nimbus-vs-openclaw.md","Nimbus vs OpenClaw: A Chat Bot on Your Phone, or a Company Workspace with Approvals?",{"label":183,"10|authors":2160},[2161],{"name":186,"to":135},{"type":167,"value":2163,"toc":2418},[2164,2171,2179,2187,2189,2247,2249,2252,2261,2267,2270,2273,2276,2280,2283,2286,2292,2294,2304,2307,2313,2320,2322,2326,2329,2333,2336,2340,2343,2347,2352,2356,2359,2363,2366,2370,2373,2377,2380,2382,2390,2392],[190,2165,2166,2170],{},[193,2167,710],{"href":2168,"rel":2169},"https://docs.openclaw.ai/",[197]," is a personal or team assistant you install and reach from the chat apps you already live in. Nimbus is a company workspace where a write into Salesforce waits for a named person — and RevOps can refuse it.",[190,2172,2173,2174,2178],{},"Both are “an agent.” They are not the same job. A WhatsApp number that can reach a shell is a privileged identity, whether the README is charming or not. The ",[193,2175,2177],{"href":2168,"rel":2176},[197],"official docs"," are clear about the audience: developers and power users who want a personal assistant they can message from anywhere, without handing their data to a hosted chatbot. That design is right for a homelab, a founder who wants Telegram on the train, or a tightly scoped internal bot that never sees customer data. It is popular because it works. Popularity is not a control system.",[190,2180,2181,2182,2186],{},"OpenClaw is an open-source project (it has also been known as Clawdbot and Moltbot) that you run on your own computer or server. One process sits in the middle; you connect Discord, Google Chat, iMessage, Microsoft Teams, Signal, Slack, Telegram, WhatsApp, and more. You pick the model. You pay that model bill. Setup can be minutes if you are comfortable installing software and pasting an API key. Community packs add tools; treat a marketplace install like unreviewed software with credentials. The ",[193,2183,1552],{"href":2184,"rel":2185},"https://github.com/openclaw/openclaw",[197]," is public. Self-hosting is the point. Self-hosting is also the obligation.",[221,2188,224],{"id":223},[226,2190,2191,2197,2202,2208,2213,2219,2224,2229],{},[229,2192,2193,2196],{},[232,2194,2195],{},"OpenClaw."," An open-source project (it has also been known as Clawdbot and Moltbot) that you run on your own computer or server. One process sits in the middle; you connect Discord, Google Chat, iMessage, Microsoft Teams, Signal, Slack, Telegram, WhatsApp, and more.",[229,2198,2199,2201],{},[232,2200,1572],{}," You pick the model. You pay that model bill. Setup can be minutes if you are comfortable installing software and pasting an API key.",[229,2203,2204,2207],{},[232,2205,2206],{},"Skills / marketplace."," Community packs that add tools. Treat a marketplace install like unreviewed software with credentials.",[229,2209,2210,2212],{},[232,2211,252],{}," In Nimbus, a shared workspace for one job — people, tools, budget, and a finish line.",[229,2214,2215,2218],{},[232,2216,2217],{},"Agent teams."," AI specialists grouped like departments, assigned to the workstream.",[229,2220,2221,2223],{},[232,2222,258],{}," Changing a live system. If an agent can edit an opportunity from a Telegram chat, you no longer have a CRM. You have a group chat with side effects.",[229,2225,2226,2228],{},[232,2227,264],{}," The record of what ran, who approved, and what changed.",[229,2230,2231,2234,2235,2240,2241,2246],{},[232,2232,2233],{},"Secure AI system development."," The ",[193,2236,2239],{"href":2237,"rel":2238},"https://www.ncsc.gov.uk/collection/guidelines-secure-ai-system-development",[197],"UK NCSC guidelines",", issued jointly with ",[193,2242,2245],{"href":2243,"rel":2244},"https://www.cisa.gov/news-events/news/dhs-cisa-and-uk-ncsc-release-joint-guidelines-secure-ai-system-development",[197],"CISA",": logging, monitoring, and not exposing sensitive data — whether you built the system or stitched it from tools and APIs.",[221,2248,279],{"id":278},[190,2250,2251],{},"Anyone who can message the bot can try to become the bot. A viral internal bot is a classic “we use AI” slide. It is also a classic reason scaling stalls: nobody can say which token the bot uses, who is allowed to talk to it, or what it changed last Tuesday. OpenClaw’s scarce resource is reach: many messaging surfaces, one agent. Nimbus’s scarce resource is control: many operators and systems, one release process.",[190,2253,2254,2255,2257,2258,2260],{},"OpenClaw memory is whatever you attached: files, a store, community packs. Two people can run two OpenClaws and disagree about last week’s decision because each bot remembered a different thread. There is no company ",[193,2256,379],{"href":378}," product and no Lifecycle Graph of releases. Nimbus memory is three places you can show a colleague: the wiki (what we claim), ",[193,2259,756],{"href":51}," (what Salesforce or the ledger claim), and the graph (what we did). That is what you show when someone asks, “What did we approve?”",[190,2262,2263,2264,2266],{},"A personal assistant on your phone and a system that updates customer records are not the same system, even if both answer in chat. The joint NCSC and CISA guidelines exist because the second one is an AI system you operate. Running the software on your own computer does not waive logging, monitoring, or ",[193,2265,695],{"href":315}," gates. Customer data in a WhatsApp-connected agent is still sensitive data in an AI system you operate. Someone else running the server reduces your upkeep. It does not give you workstreams, specialist teams, or a Lifecycle Graph. A service level on a machine is not a release process.",[190,2268,2269],{},"If an agent can edit an opportunity from a Telegram chat, you no longer have a CRM. You have a group chat with side effects. Skills from a marketplace make that easier, not safer. Treat a pack that adds tools like unreviewed software with credentials — because that is what it is.",[190,2271,2272],{},"Role by role: a developer or power user who wants Telegram on the train gets the product OpenClaw was designed for. Security should hear “privileged identity,” not “fun bot.” RevOps should refuse a write path that lives in a group chat. Finance cannot reconstruct last Tuesday from a thread only the bot remembered. IT asked to “just host it for the company” is being asked to become the platform team for a personal assistant. A COO counting GitHub stars is measuring excitement. Companies measure blast radius.",[190,2274,2275],{},"You can still want OpenClaw after a security conversation. Keep it contained: no production credentials, not a public WhatsApp number on company data, a named owner, and an exit — the proven job becomes a Nimbus workstream; the bot goes back to being personal. Personal agents can feed drafts into Nimbus workstreams. Do not let the chat bot hold write credentials to core systems.",[221,2277,2279],{"id":2278},"when-openclaw-is-a-better-fit","When OpenClaw is a better fit",[190,2281,2282],{},"Choose OpenClaw for personal productivity, home automation, and greenfield bots where you are the admin. Choose it when the blast radius is your own chats and files.",[190,2284,2285],{},"Do not choose OpenClaw as the company AI platform because it has more GitHub stars than last quarter’s shortlist. Stars measure excitement. Companies measure blast radius.",[190,2287,2288,2289,2291],{},"If you still want OpenClaw after a security conversation, keep it contained: no production credentials, not a public WhatsApp number on company data, a named owner, and an exit — the proven job becomes a Nimbus workstream; the bot goes back to being personal. Same layer as ",[193,2290,715],{"href":714},": a personal assistant you look after. OpenClaw maximises channels. Hermes maximises skills and personal memory. Neither is a company OS.",[221,2293,360],{"id":359},[190,2295,2296,2297,2299,2300,2303],{},"Nimbus is the application you log into at work. Operators do not babysit a process on a server. They open a ",[193,2298,673],{"href":32}," with ",[193,2301,2302],{"href":20},"agent teams"," and connectors.",[190,2305,2306],{},"Writes into those tools stay off until you turn them on. A quoted change sits until a human signs. You can think of Nimbus as the place OpenClaw users graduate to when the bot needs a company identity: production passwords leave the home server, writes pick up an approval, and the artefact lands where other people can find it.",[190,2308,2309,2310,2312],{},"Nimbus ",[193,2311,451],{"href":51}," are a catalogue you scope per workspace — more than 2,000 tools — read-only until write is enabled. The default if someone adds a dangerous skill is not “whatever the host allowed.” The default is: the connector cannot write until you say so.",[190,2314,2315,2316,1865,2318,275],{},"See the ",[193,2317,1700],{"href":12},[193,2319,39],{"href":40},[221,2321,415],{"id":414},[417,2323,2325],{"id":2324},"is-openclaw-a-nimbus-competitor","Is OpenClaw a Nimbus competitor?",[190,2327,2328],{},"On a spreadsheet that says “we want an agent,” yes. In practice, one is a chat assistant you install. One is a company operating system for work, approvals, and memory.",[417,2330,2332],{"id":2331},"can-we-put-openclaw-in-front-of-nimbus","Can we put OpenClaw in front of Nimbus?",[190,2334,2335],{},"Personal agents can feed drafts into Nimbus workstreams. Do not let the chat bot hold write credentials to core systems. Put those in Nimbus connector scopes.",[417,2337,2339],{"id":2338},"what-about-a-hosted-or-cloud-openclaw","What about a hosted or cloud OpenClaw?",[190,2341,2342],{},"Someone else running the server reduces your upkeep. It does not give you workstreams, specialist teams, or a Lifecycle Graph. A service level on a machine is not a release process.",[417,2344,2346],{"id":2345},"is-openclaw-the-same-as-hermes","Is OpenClaw the same as Hermes?",[190,2348,1744,2349,275],{},[193,2350,2351],{"href":714},"Nimbus vs Hermes",[417,2353,2355],{"id":2354},"does-self-hosting-mean-we-can-skip-logging-and-monitoring","Does self-hosting mean we can skip logging and monitoring?",[190,2357,2358],{},"No. Customer data in a WhatsApp-connected agent is still sensitive data in an AI system you operate. NCSC and CISA’s joint guidelines include logging, monitoring, and not exposing that data to unauthorised parties.",[417,2360,2362],{"id":2361},"can-we-standardise-the-company-on-openclaw-if-we-lock-down-who-can-message-it","Can we standardise the company on OpenClaw if we lock down who can message it?",[190,2364,2365],{},"Locking down who can talk to the bot is necessary and not sufficient. You still lack workstreams, specialist teams, a wiki, quoted writes, and a graph. A tightly scoped internal bot that never sees customer data can stay. A company platform cannot be “the bot, but with a allow-list.”",[417,2367,2369],{"id":2368},"who-owns-an-internal-openclaw","Who owns an internal OpenClaw?",[190,2371,2372],{},"Whoever runs the process owns the outcome: tokens, skills, who may message it, what it can reach. That is usually a developer, not RevOps. If the bot can change production data, you have given a personal-assistant owner a CRM duty they did not ask for. Move that duty to Nimbus governance.",[417,2374,2376],{"id":2375},"how-do-we-retire-a-viral-bot-without-a-fight","How do we retire a viral bot without a fight?",[190,2378,2379],{},"Name an exit in advance: the proven job becomes a workstream; production credentials leave the bot; the bot goes back to being personal. Stars and habit are not an argument to keep a WhatsApp number on company data.",[221,2381,490],{"id":489},[190,2383,2384,496,2386,500,2388,275],{},[193,2385,495],{"href":330},[193,2387,499],{"href":315},[193,2389,2351],{"href":714},[221,2391,508],{"id":507},[226,2393,2394,2400,2406,2412],{},[229,2395,2396],{},[193,2397,2399],{"href":2168,"rel":2398},[197],"OpenClaw documentation",[229,2401,2402],{},[193,2403,2405],{"href":2184,"rel":2404},[197],"OpenClaw on GitHub",[229,2407,2408],{},[193,2409,2411],{"href":2237,"rel":2410},[197],"UK NCSC, Guidelines for secure AI system development",[229,2413,2414],{},[193,2415,2417],{"href":2243,"rel":2416},[197],"CISA and UK NCSC joint guidelines for secure AI system development",{"title":170,"searchDepth":171,"depth":171,"links":2419},[2420,2421,2422,2423,2424,2434,2435],{"id":223,"depth":171,"text":224},{"id":278,"depth":171,"text":279},{"id":2278,"depth":171,"text":2279},{"id":359,"depth":171,"text":360},{"id":414,"depth":171,"text":415,"children":2425},[2426,2427,2428,2429,2430,2431,2432,2433],{"id":2324,"depth":544,"text":2325},{"id":2331,"depth":544,"text":2332},{"id":2338,"depth":544,"text":2339},{"id":2345,"depth":544,"text":2346},{"id":2354,"depth":544,"text":2355},{"id":2361,"depth":544,"text":2362},{"id":2368,"depth":544,"text":2369},{"id":2375,"depth":544,"text":2376},{"id":489,"depth":171,"text":490},{"id":507,"depth":171,"text":508},"OpenClaw is a self-hosted agent you message from WhatsApp or Telegram; Nimbus is the company workspace where a CRM write waits for a named person.","/blog/nimbus-vs-openclaw",{"title":2158,"description":2436},"blog/nimbus-vs-openclaw",[559,2441,2442,2443,1202],"openclaw","clawdbot","self-hosted-agents","mkJSwy_VjEhgl-I3LLmrlX3HJPAue_8wt9IUwqZt_9E",{"id":2446,"title":2447,"archived":164,"authors":165,"badge":2448,"body":2451,"date":555,"definedTerm":165,"department":165,"description":2745,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":164,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":2746,"relatedHeading":165,"seo":2747,"series":559,"sitemap":130,"status":165,"stem":2748,"subhead":165,"tags":2749,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":2753},"content/blog/nimbus-vs-paperclip.md","Nimbus vs Paperclip: An Org Chart for Other People’s Bots, or a Product a COO Can Log Into?",{"label":183,"10|authors":2449},[2450],{"name":186,"to":135},{"type":167,"value":2452,"toc":2727},[2453,2461,2471,2490,2492,2552,2554,2557,2563,2575,2578,2581,2588,2592,2598,2601,2604,2607,2609,2612,2620,2624,2626,2630,2633,2637,2640,2644,2647,2651,2654,2658,2666,2670,2675,2679,2682,2686,2689,2691,2700,2702],[190,2454,2455,2460],{},[193,2456,2459],{"href":2457,"rel":2458},"https://paperclip.ing/",[197],"Paperclip"," is the management layer people reach for when they already run OpenClaw, Hermes, Claude, Cursor, or a pile of custom workers and have lost track of who is doing what and what it costs. Nimbus is the finished product those operators log into: one shared workspace for a job, specialist teams, official playbooks, and a record of what shipped.",[190,2462,2463,2464,2466,2467,2470],{},"Paperclip is multiplayer for ",[204,2465,1201],{},". Nimbus is multiplayer for departments and the people in them. The insight behind Paperclip is correct. Multi-agent chaos is an organisation-design problem, not a prompting problem. If you have lived through “we have twelve automations, three chat bots, and a coding agent fleet,” Paperclip feels like relief. Someone finally named the org chart. Relief is not a workplace. An org chart of agents is a start. A signed-off outcome in a workstream is the product those agents would work ",[204,2468,2469],{},"in",", not the scheduler that wakes them.",[190,2472,2473,2474,2478,2479,1865,2484,2489],{},"Paperclip is an open-source app to manage AI agents for work. You define a goal, “hire” agents into roles, set monthly budgets, and run work through tickets. Agents wake on a schedule and stop when they hit the budget. The ",[193,2475,1552],{"href":2476,"rel":2477},"https://github.com/paperclipai/paperclip",[197]," is public; you can run it yourself. It works with many agents — the site lists Claude, Codex, Gemini, Cursor, Hermes, OpenClaw, and others. If a worker can receive a heartbeat, it can be hired. ",[193,2480,2483],{"href":2481,"rel":2482},"https://docs.crewai.com/",[197],"CrewAI",[193,2485,2488],{"href":2486,"rel":2487},"https://arxiv.org/abs/2308.00352",[197],"MetaGPT"," are the research-and-builder names for that orchestration category. Paperclip is that category as a product you hire into.",[221,2491,224],{"id":223},[226,2493,2494,2504,2517,2523,2528,2533,2538,2547],{},[229,2495,2496,2499,2500,2503],{},[232,2497,2498],{},"Paperclip."," An open-source app to manage AI agents for work. You define a goal, “hire” agents into roles, set monthly budgets, and run work through tickets. Agents wake on a schedule and stop when they hit the budget. The ",[193,2501,1552],{"href":2476,"rel":2502},[197]," is public; you can run it yourself.",[229,2505,2506,2509,2510,1865,2513,2516],{},[232,2507,2508],{},"Orchestration."," Coordinating several agents. ",[193,2511,2483],{"href":2481,"rel":2512},[197],[193,2514,2488],{"href":2486,"rel":2515},[197]," are the research-and-builder names for that category. Paperclip is that category as a product you hire into.",[229,2518,2519,2522],{},[232,2520,2521],{},"Agent budget."," Cap the worker, warn at 80%, pause at 100%. Necessary cost control. Not the same as stopping a bad write.",[229,2524,2525,2527],{},[232,2526,252],{}," In Nimbus, a shared workspace for one job — the ticket a non-engineer can actually run.",[229,2529,2530,2532],{},[232,2531,2217],{}," AI specialists grouped like departments: finance, go-to-market, ops. You are not wiring a cluster of other people’s bots on day one.",[229,2534,2535,2537],{},[232,2536,636],{}," Official playbooks those teams must respect.",[229,2539,2540,2542,2543,2546],{},[232,2541,258],{}," Changing a live system. Paperclip’s FAQ is frank: it governs what agents do ",[204,2544,2545],{},"to Paperclip"," (hiring, strategy). Your agents are your own, and you secure them however you want.",[229,2548,2549,2551],{},[232,2550,264],{}," What ran, who approved, and what changed — so next quarter’s team does not relitigate the exception from Slack archaeology.",[221,2553,279],{"id":278},[190,2555,2556],{},"The limitation is structural. Paperclip assumes you bring the employees (the agents), the tools, the memory, and the identity story. That is honest. It is also why a scheduler is not the product your board logs into. You still need a place work is grounded, a place writes are gated, and a place the company remembers.",[190,2558,2559,2560,2562],{},"A worker that hits its budget and stops is a cost control. A worker that hits production with the wrong SKU is an incident. Nimbus also caps spend so a long-running job cannot silently burn the month (metered in NTUs — work credits). The extra loop is change control: which system a write hits, who signs, where the artefact is stored. See ",[193,2561,1202],{"href":40},". Cap-at-100% is necessary. It is not the same as stopping a bad write.",[190,2564,2565,2566,2568,2569,2571,2572,2574],{},"Paperclip does not replace a knowledge layer. Each hired agent may remember differently — Hermes how-to notes here, OpenClaw files there, a folder nobody owns. Different agents will each tell you a different last quarter. Nimbus ships wiki plus ",[193,2567,756],{"href":51}," plus the ",[193,2570,23],{"href":391}," so execution has one place to read from and a gated place to write to. Paperclip’s FAQ is frank: it governs what agents do ",[204,2573,2545],{}," (hiring, strategy). Your agents are your own, and you secure them however you want. That frankness is a virtue. It is also the gap. Write-back into Salesforce is not Paperclip’s job unless you built it into the workers you hired.",[190,2576,2577],{},"Speed of new agents is exactly why a scheduler appears. It is also why a scheduler is not the office. A staff rota does not replace the workplace. It only says who is on shift. OpenClaw and Hermes are employees. Paperclip is the org chart. Nimbus is the company plus the office. Buying all three still does not give you a Lifecycle Graph unless Nimbus (or something like it) is in the stack.",[190,2579,2580],{},"Role by role: an engineer running OpenClaw, Hermes, and a coding fleet will feel Paperclip as relief — budgets, tickets, a heartbeat. A Head of Ops should not be asked to assemble that roster on day one; they need a product they can log into. Finance cares that a pause-at-budget is not a pause-at-bad-journal. Security inherits whatever each hired agent can already do; Paperclip does not secure them for you. A COO comparing open source versus a hosted product is choosing which lock they can staff: Paperclip reduces vendor lock-in and increases ops lock-in. Most companies can complete a vendor review. Few can run a round-the-clock agent operations desk.",[190,2582,2583,2584,2587],{},"If you are committed to those workers and only need orchestration, Paperclip is in-category. If you are not building an OS, do not start with the scheduler. Treat the workers as prototypes. Recreate the ",[204,2585,2586],{},"jobs"," as Nimbus workstreams and agent teams. Leave the old bots as personal tools without production credentials. Do not lift-and-shift tickets. Lift-and-shift the operating loop.",[221,2589,2591],{"id":2590},"when-paperclip-is-a-better-fit","When Paperclip is a better fit",[190,2593,2594,2595,2597],{},"Choose Paperclip when you are committed to OpenClaw, Hermes, or custom workers, you have people to operate them, and you only need orchestration. Choose it as a research scheduler in a lab. Choose it if your company ",[204,2596,1964],{}," building an agent OS and you need that scheduler while you build the rest.",[190,2599,2600],{},"If you are not building an OS, do not start with the scheduler. A staff rota does not replace the office. It only says who is on shift.",[190,2602,2603],{},"Paperclip’s value shows up when you have several different workers to coordinate. Nimbus’s value shows up at one team that must touch production systems safely. You do not need Paperclip if you only have one agent. You might still need Nimbus.",[190,2605,2606],{},"Do not put a second org chart on top of Nimbus. Nimbus already assigns work to agent teams. Two budgets and two sources of truth is a support nightmare. If you migrate, migrate jobs, not tickets.",[221,2608,360],{"id":359},[190,2610,2611],{},"Nimbus is the application layer a Head of Ops opens without assembling a roster of third-party bots on day one.",[190,2613,2614,2615,1865,2617,2619],{},"You attach connectors under a read-only default. Humans release writes. You get specialist teams and a canvas, then you attach systems. See ",[193,2616,2302],{"href":20},[193,2618,374],{"href":32},". Spend is capped in NTUs so a long-running job cannot silently burn the month — and the write still waits for a signer.",[190,2621,1697,2622,275],{},[193,2623,1700],{"href":12},[221,2625,415],{"id":414},[417,2627,2629],{"id":2628},"is-nimbus-paperclip-with-a-nicer-screen","Is Nimbus “Paperclip with a nicer screen”?",[190,2631,2632],{},"No. The overlap is control: roles, budgets, assignment. The product is the work loop and the graph. A ticket router does not give you official playbooks or a read-only-default CRM connector.",[417,2634,2636],{"id":2635},"can-paperclip-orchestrate-nimbus","Can Paperclip orchestrate Nimbus?",[190,2638,2639],{},"Unnatural. Nimbus already assigns work to agent teams. A second org chart on top is two budgets, two sources of truth, and a support nightmare.",[417,2641,2643],{"id":2642},"open-source-vs-a-hosted-product-which-lock-in-is-worse","Open source vs a hosted product — which lock-in is worse?",[190,2645,2646],{},"Paperclip reduces vendor lock-in and increases ops lock-in: you staff the bots. Nimbus is the reverse. Pick the lock you can actually staff. Most companies can complete a vendor review. Few can run a round-the-clock agent operations desk.",[417,2648,2650],{"id":2649},"do-we-need-paperclip-if-we-only-have-one-agent","Do we need Paperclip if we only have one agent?",[190,2652,2653],{},"No. Paperclip’s value shows up when you have several different workers to coordinate. Nimbus’s value shows up at one team that must touch production systems safely.",[417,2655,2657],{"id":2656},"how-does-paperclip-relate-to-openclaw-and-hermes","How does Paperclip relate to OpenClaw and Hermes?",[190,2659,2660,2661,1865,2663,2665],{},"OpenClaw and Hermes are employees. Paperclip is the org chart. Nimbus is the company plus the office. See ",[193,2662,1747],{"href":709},[193,2664,2351],{"href":714},". Buying all three still does not give you a Lifecycle Graph.",[417,2667,2669],{"id":2668},"can-we-migrate-from-paperclip-to-nimbus","Can we migrate from Paperclip to Nimbus?",[190,2671,2672,2673,2587],{},"Treat the workers as prototypes. Recreate the ",[204,2674,2586],{},[417,2676,2678],{"id":2677},"does-a-budget-cap-replace-write-back-governance","Does a budget cap replace write-back governance?",[190,2680,2681],{},"No. A worker that hits its budget and stops is a cost control. A worker that hits production with the wrong SKU is an incident. Caps are necessary. They do not quote a field change or name a signer.",[417,2683,2685],{"id":2684},"who-should-run-paperclip-if-we-keep-it","Who should run Paperclip if we keep it?",[190,2687,2688],{},"Whoever already operates the bots — usually engineering. Do not hand a Head of Ops a scheduler and call it a workplace. If operators need to finish a job, they need Nimbus. If engineers need to wake a fleet, they may still want Paperclip in the lab, off production credentials.",[221,2690,490],{"id":489},[190,2692,2693,496,2695,500,2698,275],{},[193,2694,1145],{"href":1144},[193,2696,2697],{"href":373},"What is an AI workstream",[193,2699,1747],{"href":709},[221,2701,508],{"id":507},[226,2703,2704,2709,2715,2721],{},[229,2705,2706],{},[193,2707,2459],{"href":2457,"rel":2708},[197],[229,2710,2711],{},[193,2712,2714],{"href":2476,"rel":2713},[197],"Paperclip on GitHub",[229,2716,2717],{},[193,2718,2720],{"href":2481,"rel":2719},[197],"CrewAI documentation",[229,2722,2723],{},[193,2724,2726],{"href":2486,"rel":2725},[197],"Hong et al., MetaGPT (arXiv:2308.00352)",{"title":170,"searchDepth":171,"depth":171,"links":2728},[2729,2730,2731,2732,2733,2743,2744],{"id":223,"depth":171,"text":224},{"id":278,"depth":171,"text":279},{"id":2590,"depth":171,"text":2591},{"id":359,"depth":171,"text":360},{"id":414,"depth":171,"text":415,"children":2734},[2735,2736,2737,2738,2739,2740,2741,2742],{"id":2628,"depth":544,"text":2629},{"id":2635,"depth":544,"text":2636},{"id":2642,"depth":544,"text":2643},{"id":2649,"depth":544,"text":2650},{"id":2656,"depth":544,"text":2657},{"id":2668,"depth":544,"text":2669},{"id":2677,"depth":544,"text":2678},{"id":2684,"depth":544,"text":2685},{"id":489,"depth":171,"text":490},{"id":507,"depth":171,"text":508},"Paperclip organises the agents you already run; Nimbus is the finished workplace where departments share one job — not twelve bots nobody owns.","/blog/nimbus-vs-paperclip",{"title":2447,"description":2745},"blog/nimbus-vs-paperclip",[559,2750,2751,2752,1202],"paperclip","multi-agent","orchestration","8qJ1VEs3LjEJM6C34ivw1dEAOQerIHWkW1Pe4DOr6oo",{"id":2755,"title":2756,"archived":164,"authors":165,"badge":2757,"body":2760,"date":555,"definedTerm":165,"department":165,"description":3059,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":164,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":3060,"relatedHeading":165,"seo":3061,"series":559,"sitemap":130,"status":165,"stem":3062,"subhead":165,"tags":3063,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":3066},"content/blog/nimbus-vs-perplexity.md","Nimbus vs Perplexity: Cited Answers from the Web, or Running the Work the Answer Implies?",{"label":183,"10|authors":2758},[2759],{"name":186,"to":135},{"type":167,"value":2761,"toc":3040},[2762,2770,2773,2793,2795,2845,2847,2853,2871,2874,2880,2887,2890,2894,2897,2900,2903,2906,2908,2917,2925,2931,2935,2937,2941,2944,2948,2951,2955,2958,2962,2965,2969,2975,2979,2982,2986,2989,2993,2996,3000,3003,3005,3013,3015],[190,2763,2764,2769],{},[193,2765,2768],{"href":2766,"rel":2767},"https://www.perplexity.ai/enterprise",[197],"Perplexity Enterprise"," is how people get cited answers from the web, and increasingly from files and connected tools. Nimbus is how the company runs the work those answers imply: a shared job, official playbooks, a human on the write.",[190,2771,2772],{},"If your bottleneck is “get a sourced answer fast,” Perplexity is in-category. If your bottleneck is “update the live recommendation without a shadow login,” Nimbus is in-category. Those are different verbs. Perplexity synthesises. Nimbus runs work. Do not shortlist an answer engine as a stealth operating system, and do not shortlist a work OS as the only web research tool.",[190,2774,2775,2780,2781,2786,2787,2792],{},[193,2776,2779],{"href":2777,"rel":2778},"https://www.perplexity.ai/hub/blog/perplexity-launches-enterprise-pro",[197],"Perplexity’s launch note for Enterprise Pro"," is the original B2B pitch: team management, SSO, SOC 2, and a promise not to train on enterprise customer data. Their later ",[193,2782,2785],{"href":2783,"rel":2784},"https://www.perplexity.ai/hub/blog/how-perplexity-enterprise-pro-keeps-your-data-secure",[197],"security write-up"," is where those promises live in more detail. ",[193,2788,2791],{"href":2789,"rel":2790},"https://www.perplexity.ai/help-center/en/articles/10672063-introduction-to-perplexity-connectors-for-enterprise-orgs",[197],"Enterprise connectors"," can pull files from Drive, OneDrive, and SharePoint into that answer loop. Deep research and Computer-style loops browse and assemble memos, decks, and dashboards — still orbiting the thread that answers a question. That is a legitimate category. Perplexity trained a generation to expect synthesis with links, not a blue list of pages.",[221,2794,224],{"id":223},[226,2796,2797,2803,2809,2815,2821,2826,2831,2836],{},[229,2798,2799,2802],{},[232,2800,2801],{},"Answer engine."," You ask; you get a synthesis with links, not a blue list of pages. Perplexity trained a generation to expect that.",[229,2804,2805,2808],{},[232,2806,2807],{},"Enterprise Pro."," Perplexity’s B2B workspace: team management, SSO, SOC 2, and a promise not to train on enterprise customer data.",[229,2810,2811,2814],{},[232,2812,2813],{},"Connectors (Perplexity)."," Pull files from Drive, OneDrive, and SharePoint into the answer loop. The right standard for an answer engine people will upload files into. Not a write gate on a retailer portal.",[229,2816,2817,2820],{},[232,2818,2819],{},"Deep research / Computer."," Longer browse-and-assemble loops — memos, decks, dashboards — still orbiting the thread that answers a question.",[229,2822,2823,2825],{},[232,2824,252],{}," In Nimbus, a shared workspace for one job — not another search thread.",[229,2827,2828,2830],{},[232,2829,636],{}," Official playbooks: how we change assortment, who signs, what “done” means.",[229,2832,2833,2835],{},[232,2834,258],{}," Changing a live system. You do not want an answer engine holding production credentials.",[229,2837,2838,2841,2842,2844],{},[232,2839,2840],{},"Perception."," Asking Nimbus in ordinary language over ",[204,2843,301],{}," graph, wiki, and scoped systems — with the next step being a workstream, not another search.",[221,2846,279],{"id":278},[190,2848,2849,2850,2852],{},"It is also not workplace search. ",[193,2851,1218],{"href":1954}," is permission-aware find-the-file across the apps your company already uses. Perplexity is web-native synthesis that can also ingest your stuff. Do not shortlist them as the same line on an RFP. Connectors that pull Drive, OneDrive, and SharePoint into the answer loop are the right standard for an answer engine people will upload files into. They are not years of crawl-and-permission engineering, and they are not a write gate on a retailer portal.",[190,2854,2855,2856,2859,2860,2863,2864,2867,2868,2870],{},"Perplexity’s trust story is provenance of ",[204,2857,2858],{},"claims",": links, snippets, a trail a human can click. That is the right standard for web research. Limits: memory of ",[204,2861,2862],{},"decisions"," is still thread-shaped unless you file the answer somewhere else. Nimbus’s trust story is provenance of ",[204,2865,2866],{},"actions",": who ran, what the wiki said, what was approved, what changed in a live system. Public-web citations may appear inside a workstream. They are not the product. The ",[193,2869,23],{"href":391}," is.",[190,2872,2873],{},"SOC 2 and a non-training term make the research workspace safer to use. They do not turn a brief into a signed portal update. Uploading customer or employee files into any research workspace is still your processing. Those terms help. They do not replace a purpose for what you put in the box, and they do not replace a human on a production login. Perplexity Enterprise governance is mostly “who may ask and what corpus they see.” Nimbus governance is “who may change what.” Different verb.",[190,2875,2876,2877,2879],{},"A healthy pattern: Perplexity (or another search-grounded assistant) for the public-web pass; Nimbus for the company pass and the write. Do not paste a Perplexity answer into Salesforce — or a retailer portal — as if it were a ",[193,2878,316],{"href":315},". If you force Perplexity to do the operational job, you will bolt on brittle browser clicking and call it operations. If you force Nimbus to be the only web research tool, you will underuse an engine that is very good at cited public synthesis.",[190,2881,2882,2883,2886],{},"Role by role: a researcher or strategist wants cited answers from the web — Perplexity is in-category. A knowledge-work programme wants SSO, SOC 2, and a non-training term so people stop using the consumer tab; that is Enterprise Pro doing its job. RevOps and merchandising need the answer to become a signed change in a live system, not another thread. Legal cares what you uploaded into the research workspace; SOC 2 helps and does not replace purpose. Marketing should not buy Perplexity because “we need to show up in answer engines” — getting found is marketing; running the company is operations. Security should block ",[204,2884,2885],{},"production credentials"," in any research agent, not necessarily block Perplexity itself.",[190,2888,2889],{},"Three verbs sit near each other on RFPs. Perplexity synthesises (especially the web). Glean finds (especially workplace files with source permissions). Nimbus runs work. Most large companies will eventually own at least two.",[221,2891,2893],{"id":2892},"when-perplexity-is-a-better-fit","When Perplexity is a better fit",[190,2895,2896],{},"Choose Perplexity when the job is web-grounded research with citations, you do not need gated writes, and you want an answer engine as the daily UX. Choose it as a complement to Nimbus, not as a stealth OS.",[190,2898,2899],{},"Do not choose Perplexity because “we need to show up in answer engines.” Getting found is marketing. Running the company is operations.",[190,2901,2902],{},"If you force Perplexity to do the operational job, you will bolt on brittle browser clicking and call it operations. If you force Nimbus to be the only web research tool, you will underuse an engine that is very good at cited public synthesis.",[190,2904,2905],{},"Keep an answer engine for public-web research if it helps. Route execution to Nimbus. That is a data-handling rule plus an operating model, not a ban. Block production credentials in any research agent. Allow cited research.",[221,2907,360],{"id":359},[190,2909,2910,2911,2913,2914,2916],{},"A ",[193,2912,673],{"href":32}," is the job after the brief. ",[193,2915,383],{"href":51}," link to the tools you already run: internal sales, a research feed if you have one, the portal if you attach it. Reads first. Writes off until a named person releases them.",[190,2918,2919,2920,409,2922,2924],{},"Nimbus can look like an answer box when you ask the business a question. It is not Perplexity. See ",[193,2921,395],{"href":36},[193,2923,1700],{"href":12},". Perception is ordinary language over the Lifecycle Graph, policies, teams, and integrations — in a product where the next step is governed work. It is not a citation engine over the public web.",[190,2926,2927,2928,2930],{},"A research-shaped ",[193,2929,677],{"href":20}," is grounded in wiki playbooks plus connectors, then a human release, then a graph record you can query next quarter.",[190,2932,406,2933,275],{},[193,2934,39],{"href":40},[221,2936,415],{"id":414},[417,2938,2940],{"id":2939},"does-nimbus-replace-perplexity","Does Nimbus replace Perplexity?",[190,2942,2943],{},"No. Keep an answer engine for public-web research if it helps. Nimbus Perception is for company graph, wiki, and scoped systems.",[417,2945,2947],{"id":2946},"does-perplexity-replace-nimbus","Does Perplexity replace Nimbus?",[190,2949,2950],{},"Only if “ask the web” is the entire AI programme. It does not replace workstreams, agent teams, or write gates.",[417,2952,2954],{"id":2953},"is-asking-nimbus-just-perplexity-on-internal-data","Is asking Nimbus just Perplexity on internal data?",[190,2956,2957],{},"No. Perception is ordinary language over the Lifecycle Graph, policies, teams, and integrations — in a product where the next step is governed work. It is not a citation engine over the public web.",[417,2959,2961],{"id":2960},"perplexity-vs-glean-vs-nimbus","Perplexity vs Glean vs Nimbus?",[190,2963,2964],{},"Perplexity synthesises (especially the web). Glean finds (especially workplace files with source permissions). Nimbus runs work. Three verbs. Most large companies will eventually own at least two.",[417,2966,2968],{"id":2967},"should-we-block-perplexity-if-we-buy-nimbus","Should we block Perplexity if we buy Nimbus?",[190,2970,2971,2972,2974],{},"Not by default. Block ",[204,2973,2885],{}," in any research agent. Allow cited research. Route execution to Nimbus. That is a data-handling rule plus an operating model, not a ban.",[417,2976,2978],{"id":2977},"can-we-paste-perplexity-answers-into-salesforce","Can we paste Perplexity answers into Salesforce?",[190,2980,2981],{},"You can. You should not treat that paste as a release. Provenance of claims (links you can click) is not provenance of actions (who signed, what changed). File the brief into a workstream if the next step is a live-system update.",[417,2983,2985],{"id":2984},"who-should-own-perplexity-vs-nimbus","Who should own Perplexity vs Nimbus?",[190,2987,2988],{},"Research, strategy, and often the knowledge-work programme own the answer engine: who may ask, what files may be uploaded, SSO. Line operators own Nimbus workstreams that change assortment, CRM, or portals. Legal reviews what goes in the box. Security reviews credentials, not the existence of citations.",[417,2990,2992],{"id":2991},"do-perplexity-connectors-mean-it-is-now-a-work-os","Do Perplexity connectors mean it is now a work OS?",[190,2994,2995],{},"No. Pulling Drive, OneDrive, and SharePoint into an answer loop is the right standard for a research workspace. It is not a write gate, not a workstream, and not a Lifecycle Graph. Deep research that assembles a memo is still a thread that answers a question.",[417,2997,2999],{"id":2998},"what-should-a-procurement-pack-actually-compare","What should a procurement pack actually compare?",[190,3001,3002],{},"Compare a week of work, not a list of logos. For Perplexity, the test is: can a named role get a cited answer on an approved corpus without uploading a customer file to a personal account? For Nimbus, the test is: can the same organisation take that brief into a scoped job, keep CRM read-only until a named person signs, and still reconstruct the change next quarter? If the pack only asks “do you have connectors,” both products will look the same and you will have bought the wrong week.",[221,3004,490],{"id":489},[190,3006,3007,496,3009,500,3011,275],{},[193,3008,1452],{"href":1451},[193,3010,499],{"href":315},[193,3012,2089],{"href":1954},[221,3014,508],{"id":507},[226,3016,3017,3022,3028,3034],{},[229,3018,3019],{},[193,3020,2768],{"href":2766,"rel":3021},[197],[229,3023,3024],{},[193,3025,3027],{"href":2777,"rel":3026},[197],"Perplexity launches Enterprise Pro",[229,3029,3030],{},[193,3031,3033],{"href":2783,"rel":3032},[197],"How Perplexity Enterprise Pro keeps your data secure",[229,3035,3036],{},[193,3037,3039],{"href":2789,"rel":3038},[197],"Introduction to Perplexity connectors for enterprise orgs",{"title":170,"searchDepth":171,"depth":171,"links":3041},[3042,3043,3044,3045,3046,3057,3058],{"id":223,"depth":171,"text":224},{"id":278,"depth":171,"text":279},{"id":2892,"depth":171,"text":2893},{"id":359,"depth":171,"text":360},{"id":414,"depth":171,"text":415,"children":3047},[3048,3049,3050,3051,3052,3053,3054,3055,3056],{"id":2939,"depth":544,"text":2940},{"id":2946,"depth":544,"text":2947},{"id":2953,"depth":544,"text":2954},{"id":2960,"depth":544,"text":2961},{"id":2967,"depth":544,"text":2968},{"id":2977,"depth":544,"text":2978},{"id":2984,"depth":544,"text":2985},{"id":2991,"depth":544,"text":2992},{"id":2998,"depth":544,"text":2999},{"id":489,"depth":171,"text":490},{"id":507,"depth":171,"text":508},"Perplexity is an answer engine with sources; Nimbus is the work OS that turns those answers into a signed change in the systems you already run.","/blog/nimbus-vs-perplexity",{"title":2756,"description":3059},"blog/nimbus-vs-perplexity",[559,143,3064,3065,563],"answer-engines","research","ybQ4KPnrUv_vSRDtTP65CGOUCg9FLF00np0ajH-ATAM",{"id":3068,"title":3069,"archived":164,"authors":165,"badge":3070,"body":3073,"date":555,"definedTerm":165,"department":165,"description":3377,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":164,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":3378,"relatedHeading":165,"seo":3379,"series":559,"sitemap":130,"status":165,"stem":3380,"subhead":165,"tags":3381,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":3385},"content/blog/nimbus-vs-salesforce-agentforce.md","Nimbus vs Salesforce Agentforce: The Right Agent Inside Salesforce, or Work Across the Company?",{"label":183,"10|authors":3071},[3072],{"name":186,"to":135},{"type":167,"value":3074,"toc":3359},[3075,3087,3090,3093,3095,3145,3147,3168,3171,3177,3190,3193,3207,3210,3219,3222,3226,3229,3232,3235,3237,3243,3248,3254,3256,3260,3263,3267,3270,3274,3277,3281,3284,3288,3291,3295,3303,3307,3313,3317,3320,3322,3332,3334],[190,3076,3077,3082,3083,3086],{},[193,3078,3081],{"href":3079,"rel":3080},"https://www.salesforce.com/agentforce/",[197],"Salesforce Agentforce"," is the right agent ",[204,3084,3085],{},"inside Salesforce",". Nimbus is for work that also involves Drive, legal, and finance — with a lasting record of who signed off.",[190,3088,3089],{},"Nimbus will call Salesforce. It does not try to be Salesforce. That is the point. CRM platforms that pretend to be the only operating layer become unmaintainable outside the org. Operating layers that pretend to be CRM become untrustworthy on pipeline. Customer and pipeline truth live in Salesforce. Cross-department jobs that also live in Drive and legal email need a place that is not only field history on the opportunity.",[190,3091,3092],{},"Agentforce (including Agentforce 360) is Salesforce’s agent product family sitting on Sales, Service, Marketing, Commerce, and related clouds. The 2026 shape that matters to operators: a reasoning engine that can follow scripted, reliable steps and call a model only where judgment is required; a builder where admins put conditionals and hand-offs in a readable script, not only in a prompt; Data 360 (formerly Data Cloud) as the profile fabric; and actions that update records, launch flows, call APIs, and behave the way your industry cloud already behaves. Model choice inside Salesforce is expanding (OpenAI, Anthropic on Amazon’s cloud, Google’s Gemini among options). Service-grade voice and channels come with Salesforce-shaped auditability. The buyer is usually the Salesforce platform owner, RevOps, or customer service.",[221,3094,224],{"id":223},[226,3096,3097,3103,3109,3115,3120,3125,3134,3139],{},[229,3098,3099,3102],{},[232,3100,3101],{},"Agentforce / Agentforce 360."," Salesforce’s agent product family sitting on Sales, Service, Marketing, Commerce, and related clouds.",[229,3104,3105,3108],{},[232,3106,3107],{},"Data 360."," Formerly Data Cloud. The layer that unifies customer profiles and unstructured context inside Salesforce.",[229,3110,3111,3114],{},[232,3112,3113],{},"Einstein Trust Layer."," Grounding in CRM data, masking of sensitive fields, toxicity detection, an audit trail, and zero data retention with LLM partners. CRM-native trust. Not a company-wide work ledger.",[229,3116,3117,3119],{},[232,3118,252],{}," In Nimbus, a shared workspace for one job that can include Drive, legal, and finance on the same canvas as CRM.",[229,3121,3122,3124],{},[232,3123,636],{}," Official playbooks — including when a discount is an exception.",[229,3126,3127,3129,3130,3133],{},[232,3128,258],{}," Changing a live system. Writes to Salesforce are first-class in Agentforce. In Nimbus they are ",[204,3131,3132],{},"not"," default-on. They are gated, quoted, and recorded.",[229,3135,3136,3138],{},[232,3137,264],{}," A lasting record of the programme, not only the field history on the opportunity.",[229,3140,3141,3144],{},[232,3142,3143],{},"Agent graph (Agentforce)."," A reasoning map for a turn. Not the same as Nimbus’s operational ledger.",[221,3146,279],{"id":278},[190,3148,3149,3150,3155,3156,3161,3162,3167],{},"Success looks like: a service agent resolves a case, a sales agent updates opportunity fields, a flow still fires, the admin can preview what the agent did on the record. Grounding is strongest where Data 360 and the org are clean. It is weakest where the work is not a Salesforce object. Trust inside that org is the ",[193,3151,3154],{"href":3152,"rel":3153},"https://developer.salesforce.com/docs/ai/agentforce/guide/trust.html",[197],"Einstein Trust Layer",". Salesforce’s ",[193,3157,3160],{"href":3158,"rel":3159},"https://www.salesforce.com/artificial-intelligence/trusted-ai/",[197],"Trusted AI"," pages and the ",[193,3163,3166],{"href":3164,"rel":3165},"https://trailhead.salesforce.com/content/learn/modules/the-einstein-trust-layer/meet-the-einstein-trust-layer",[197],"Trailhead Trust Layer module"," describe the same stack: grounding in CRM data, masking of sensitive fields, toxicity detection, an audit trail, and zero data retention with LLM partners. That is CRM-native trust. It is not a company-wide work ledger.",[190,3169,3170],{},"Two jobs get conflated in every Agentforce demo.",[190,3172,3173,3176],{},[232,3174,3175],{},"Update the next step on the opportunity."," Agentforce is the native answer. A sales agent with actions on Opportunity, maybe a flow, maybe a Slack ping via Salesforce. Ideal if the work already lives in Salesforce. Writes to Salesforce are first-class. Sharing rules are the permission model. That is the product working as designed.",[190,3178,3179,3182,3183,3185,3186,3189],{},[232,3180,3181],{},"Write the pricing-exception memo, involve legal, update CRM, and file what happened."," You can script pieces in Agentforce. Legal, Drive, and the memo are someone else’s system unless you pipe everything into Data 360. In Nimbus, this is a ",[193,3184,673],{"href":373},": connector scopes, a person on the write, Salesforce still the official home of the opportunity, Nimbus the place the cross-department job ran. The Trust Layer is how Salesforce keeps CRM data from leaking into LLM partners and how it logs prompts, toxicity scores, and user feedback ",[204,3187,3188],{},"on the record",". A pricing exception that also lives in Drive and legal email is a cross-function workflow. Do not ask the Trust Layer to be the memo, the legal comment, and the named signer outside the org.",[190,3191,3192],{},"A healthy split:",[3194,3195,3196,3199,3202],"ol",{},[229,3197,3198],{},"Customer and pipeline truth live in Salesforce (plus Data 360 if you have paid for unification).",[229,3200,3201],{},"Agentforce handles in-CRM actions where Salesforce sharing rules are the product.",[229,3203,3204,3205,275],{},"Nimbus agents read Salesforce under connector scope, operate across the rest of the stack, and write back only through ",[193,3206,1202],{"href":40},[190,3208,3209],{},"Skipping (1) and asking any operating layer to “just know ARR” is how you ship two pipelines. Dual write without a field-level policy is how you get sync fights. Default: Agentforce for interactive, in-CRM actions; Nimbus for batched, cross-system, approval-heavy programmes. Read-only Nimbus plus Agentforce writes is a valid starting posture. Agree the fields.",[190,3211,3212,3213,3216,3217,275],{},"Role by role: a Salesforce platform owner, RevOps, or customer-service lead wants an agent on a Salesforce object — Agentforce is the fit, including service voice and in-app sales agents. Legal and finance sitting on a pricing exception need a canvas that is not only the org. Security will like the Trust Layer for CRM data and LLM partners, and still want a ledger of releases that is not only field history. A CIO who already paid for Einstein or Agentforce credits should ",[204,3214,3215],{},"use"," Agentforce where it is strong, not stretch it into an operating layer because the credits are sunk. Credits on CRM turns do not buy you model choice across the rest of the business, or a graph of non-CRM decisions. See ",[193,3218,426],{"href":45},[190,3220,3221],{},"Both mention graphs. They are not the same. Agentforce’s agent graph is a reasoning map for a turn. Nimbus’s Lifecycle Graph is an operational ledger of work, agents, and releases. Collapsing the terms is how you buy a CRM agent and think you bought institutional memory.",[221,3223,3225],{"id":3224},"when-agentforce-is-a-better-fit","When Agentforce is a better fit",[190,3227,3228],{},"Choose Agentforce when the job is an agent on a Salesforce object, sharing rules are the permission model you need, and Data 360 is (or will be) the profile fabric. Choose it for service voice, in-app sales agents, and any workflow that should never leave the org.",[190,3230,3231],{},"Do not choose Agentforce as a stealth company operating layer. You will spend a year on Data 360 and agent scripts and still lack workstreams for everything that is not a Salesforce record.",[190,3233,3234],{},"Some organisations will run both. That is coherent if you do not pretend Agentforce’s turn-by-turn reasoning graph is a Lifecycle Graph. Attach Salesforce as a connector, keep Nimbus read-only at first, open writes through governance where the programme is batched and cross-system. Agentforce plus Data 360 is the Salesforce-platform path. They can coexist.",[221,3236,360],{"id":359},[190,3238,3239,3240,3242],{},"Nimbus’s knowledge is wiki plus ",[193,3241,756],{"href":51}," plus Lifecycle Graph. Wiki is how we run the business. Connectors are live systems — Salesforce is one of them, not the universe. The graph is what we decided after we saw the account.",[190,3244,399,3245,3247],{},[193,3246,402],{"href":12}," and attach Salesforce as a connector. Agentforce at scale is a Salesforce implementation: Data 360, sharing, agent scripts, often a partner. That is rational inside CRM. It is not how you stand up cross-company AI work. You do not need a Salesforce consulting partner to use Nimbus with Salesforce. Attach it, keep it read-only, open writes through governance.",[190,3249,406,3250,409,3252,275],{},[193,3251,374],{"href":32},[193,3253,23],{"href":24},[221,3255,415],{"id":414},[417,3257,3259],{"id":3258},"does-nimbus-replace-agentforce","Does Nimbus replace Agentforce?",[190,3261,3262],{},"Not inside Salesforce-native service and sales motions. Nimbus can read and update Salesforce through governed connectors. It should not be the official home of opportunities and cases.",[417,3264,3266],{"id":3265},"does-agentforce-replace-nimbus","Does Agentforce replace Nimbus?",[190,3268,3269],{},"Not as a place departments finish cross-system work. You can script impressive agents in the builder. You still need a company wiki, specialist teams for non-CRM work, and a ledger of releases that is not only field history.",[417,3271,3273],{"id":3272},"do-we-need-a-salesforce-consulting-partner-to-use-nimbus-with-salesforce","Do we need a Salesforce consulting partner to use Nimbus with Salesforce?",[190,3275,3276],{},"No. Attach Salesforce as a connector, keep it read-only, open writes through governance. That is the self-service path. Agentforce plus Data 360 is the Salesforce-platform path. They can coexist.",[417,3278,3280],{"id":3279},"both-mention-graphs-are-they-the-same","Both mention graphs. Are they the same?",[190,3282,3283],{},"No. Agentforce’s agent graph is a reasoning map for a turn. Nimbus’s Lifecycle Graph is an operational ledger of work, agents, and releases. Collapsing the terms is how you buy a CRM agent and think you bought institutional memory.",[417,3285,3287],{"id":3286},"should-nimbus-write-to-salesforce-or-should-agentforce","Should Nimbus write to Salesforce, or should Agentforce?",[190,3289,3290],{},"Default: Agentforce for interactive, in-CRM actions; Nimbus for batched, cross-system, approval-heavy programmes. Agree the fields. Start read-only on the Nimbus side if you need a clean split.",[417,3292,3294],{"id":3293},"we-already-paid-for-einstein-agentforce-credits-why-add-nimbus","We already paid for Einstein / Agentforce credits. Why add Nimbus?",[190,3296,3297,3298,3300,3301,275],{},"Because credits on CRM turns do not buy you model choice across the rest of the business, or a graph of non-CRM decisions. Sunk cost on Agentforce is a reason to ",[204,3299,3215],{}," Agentforce where it is strong, not a reason to stretch it into an operating layer. See ",[193,3302,426],{"href":45},[417,3304,3306],{"id":3305},"who-owns-agentforce-vs-nimbus","Who owns Agentforce vs Nimbus?",[190,3308,3309,3310,3312],{},"The Salesforce platform owner, RevOps, or customer service typically own Agentforce: sharing rules, Data 360, agent scripts. Line operators outside the org — legal, finance, teams living in Drive — own Nimbus workstreams for those jobs. Security reviews the Trust Layer ",[204,3311,2078],{}," Nimbus write gates. Do not give one “CRM AI” owner both products and expect them to notice the job split.",[417,3314,3316],{"id":3315},"can-we-start-with-read-only-nimbus-and-agentforce-writes","Can we start with read-only Nimbus and Agentforce writes?",[190,3318,3319],{},"Yes. That is a valid starting posture. Salesforce remains the system of record for the opportunity. Nimbus reads under connector scope. Writes that are interactive and in-CRM stay in Agentforce. Promote Nimbus writes later only where the programme is batched, cross-system, and approval-heavy — and only after you agree the fields.",[221,3321,490],{"id":489},[190,3323,3324,496,3326,500,3328,275],{},[193,3325,499],{"href":315},[193,3327,1455],{"href":391},[193,3329,3331],{"href":3330},"what-is-human-in-the-loop-ai","What is human-in-the-loop AI",[221,3333,508],{"id":507},[226,3335,3336,3341,3347,3353],{},[229,3337,3338],{},[193,3339,3081],{"href":3079,"rel":3340},[197],[229,3342,3343],{},[193,3344,3346],{"href":3152,"rel":3345},[197],"Agentforce Trust Layer",[229,3348,3349],{},[193,3350,3352],{"href":3158,"rel":3351},[197],"Salesforce Trusted AI",[229,3354,3355],{},[193,3356,3358],{"href":3164,"rel":3357},[197],"Trailhead: Meet the Einstein Trust Layer",{"title":170,"searchDepth":171,"depth":171,"links":3360},[3361,3362,3363,3364,3365,3375,3376],{"id":223,"depth":171,"text":224},{"id":278,"depth":171,"text":279},{"id":3224,"depth":171,"text":3225},{"id":359,"depth":171,"text":360},{"id":414,"depth":171,"text":415,"children":3366},[3367,3368,3369,3370,3371,3372,3373,3374],{"id":3258,"depth":544,"text":3259},{"id":3265,"depth":544,"text":3266},{"id":3272,"depth":544,"text":3273},{"id":3279,"depth":544,"text":3280},{"id":3286,"depth":544,"text":3287},{"id":3293,"depth":544,"text":3294},{"id":3305,"depth":544,"text":3306},{"id":3315,"depth":544,"text":3316},{"id":489,"depth":171,"text":490},{"id":507,"depth":171,"text":508},"Agentforce is the right agent layer inside Salesforce; Nimbus is for jobs that also involve Drive, legal, finance, and a lasting record of who signed off.","/blog/nimbus-vs-salesforce-agentforce",{"title":3069,"description":3377},"blog/nimbus-vs-salesforce-agentforce",[559,3382,3383,3384,563],"salesforce","agentforce","crm","2DptClsp74qe43E7tIXxaEZ7ZMzHfv2oeQ1y1qU542w",{"fold":3387,"id":3392,"title":3393,"archived":164,"authors":165,"badge":165,"body":3394,"date":165,"definedTerm":165,"department":165,"description":170,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":3398,"headline":165,"image":165,"industry":165,"jobType":165,"listed":130,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":3402,"relatedHeading":165,"seo":3403,"series":165,"sitemap":164,"status":165,"stem":3404,"subhead":165,"tags":165,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":3405},{"headline":3388,"description":3389,"primaryLabel":8,"primaryTo":3390,"secondaryLabel":3391,"secondaryTo":12},"Run frontier AI your business actually owns.","Governed agent swarms, 2,000+ integrations, and a knowledge graph that stays inside your walls. Free 7-day trial.","/checkout","Explore the platform","content/shared/cta.md","Site CTAs",{"type":167,"value":3395,"toc":3396},[],{"title":170,"searchDepth":171,"depth":171,"links":3397},[],{"headline":3399,"description":3400,"primaryLabel":8,"primaryTo":3390,"secondaryLabel":3401,"secondaryTo":99},"See what governed AI looks like on your stack.","Connect your tools, run a workstream, and keep every decision on your ledger - free for 7 days.","Talk to our team","/shared/cta",{"title":3393,"description":170},"shared/cta","wz4AdRHnaYH021WMdWcHnZvHmkZJNKaNG4XGZfnFBtw",{"enabled":164,"message":3407,"linkLabel":93,"linkHref":94,"id":3408,"title":3409,"archived":164,"authors":165,"badge":165,"body":3410,"date":165,"definedTerm":165,"department":165,"description":170,"extension":173,"eyebrow":165,"faqHeader":165,"faqs":165,"footerBand":165,"headline":165,"image":165,"industry":165,"jobType":165,"listed":130,"location":165,"navigation":130,"openRoles":165,"pageLayout":165,"path":3414,"relatedHeading":165,"seo":3415,"series":165,"sitemap":164,"status":165,"stem":3416,"subhead":165,"tags":165,"video":165,"whyJoin":165,"workplaceType":165,"__hash__":3417},"We're hiring! Join the team building the Sentient Enterprise.","content/shared/hiring.md","Hiring banner",{"type":167,"value":3411,"toc":3412},[],{"title":170,"searchDepth":171,"depth":171,"links":3413},[],"/shared/hiring",{"title":3409,"description":170},"shared/hiring","1zs3boivKda1e-b-hAyuNcmZSKjZUAXmecnwHVgcHzk",1788982427890]