Skip to content
60x
  • Company Brain
  • Knowledge Graph
  • Industries
  • About
  • Case Studies
  • Blog
Book a demo →Book a demo →
All posts
Company Brain•20 Nov 2026•16 min read•Fergus McKenzie-Wilson

What is a company brain?

A working definition, the tools behind it, and ten tests for a shared company memory that people and agents can trust.

Key takeaways

  • A company brain joins knowledge around customers, people, projects and decisions, with sources, dates and access rules attached.
  • Connected sources, identity matching, permissions and evidence-linked write-back need to work together; a product label cannot establish that they do.
  • Evaluate it on real questions, including restricted sources, changed facts, lookalike companies, missing evidence and a complete export.

On this page

  1. A working definition
  2. What gets called a company brain
  3. What goes in
  4. How one is built
  5. Answer, push, act and remember
  6. More AI work makes shared context more valuable
  7. Ten tests for a company brain
  8. What it cannot do for you
  9. Start with one expensive question
  10. Sources
  11. Frequently asked questions
  12. Related reading

A company brain is a shared model of what a company knows. It connects the systems where work happens, keeps the sources and access rules behind each answer, and gives people and AI agents a record they can build on.

At a private equity firm, that might mean joining a company's history across banker decks, meetings and the CRM. At a software business, it might mean keeping a sales promise connected to the delivery decision that changed it. In both cases, the answer needs to reflect who is asking.

The phrase has become popular. Garry Tan of Y Combinator gave a talk at AI Engineer World's Fair 2026 called Every company should have a Brain. Gartner put AI context platforms among its technology trends for 2027. Forrester called context engineering and ContextOps the missing foundation for scaling agentic AI.

The label now covers a wiki, a folder of agent notes, enterprise search and several other useful tools. A client gave us a better way to judge them. Before a pilot, its lead wrote down seven requirements: aggregated, consistent, time-aware, permission-aware, self-maintaining, auditable and sovereign. Each word can be tested.

One Label, Different Tools
Wiki or handbookAn edited account of how the company works.
Enterprise searchFind material across connected systems.
Memory filesGive an agent notes for a defined job.
Fine-tuned modelTeach a format, behaviour or specialist task.
Assistant with connectorsReach the sources from a familiar assistant.
Vector databaseRetrieve passages related to a question.
The specification
AggregatedConsistentTime-awarePermission-awareSelf-maintainingAuditableSovereign
Use the seven properties to evaluate an implementation. The product category alone cannot answer them.

The Definition

A working definition

A company brain is a shared, permissioned and time-aware model of what a company knows, built from the systems where work happens, which people and agents read from and write back to.

Shared means people and agents work from the same underlying record. Their answers can differ because their access differs. The evidence and identity rules remain consistent.

A model of what the company knows joins information around customers, people, projects, deals and decisions. Documents provide evidence about those things. The reader can follow a customer from a CRM record to a meeting, a proposal and the decision made afterwards.

Built from the systems where work happens means that connected sources feed the record. Someone still owns the source selection, access and quality checks. They should be able to spend their time governing the knowledge instead of rewriting it into another handbook.

Permissioned and time-aware means each answer depends on who can see the evidence and when that evidence was true. A current price and a superseded price can coexist without becoming two equally plausible answers.

Read and written means finished work can become evidence for the next task. A researcher contributes findings with their sources. A team approves a decision and keeps its reasons. Write-back needs its own access rules and review.

Seven properties to ask for in a company brain
Property What it means in practice
Aggregated The sources a use case needs join around the same customers, people and projects.
Consistent Different names for the same entity resolve to one record, with lookalikes kept apart.
Time-aware Facts retain their dates and replacement history.
Permission-aware Each passage retains its source's access rules, enforced when it is retrieved.
Self-maintaining Connected sources refresh on an agreed schedule, with freshness measured.
Auditable A claim can be traced to the passage, file and date behind it.
Sovereign The company chooses where its context runs and can export it with its relationships and evidence.
The Definition, Part By Part
People and agents query one underlying company record. Their access determines which evidence they can use.
One project history, available to its authorised team.
Select a part of the definition to see the behaviour it requires.

The Building Blocks

What gets called a company brain

Six approaches appear under the name. Products often combine them, and some already provide several of the properties above. Evaluate the implementation against your questions.

A wiki or handbook

A handbook gives people an edited account of how the company works. It can be an excellent source for a brain. Its freshness depends on someone maintaining it, and decisions made in meetings or chat can take time to reach the page.

Enterprise search

Search helps people find material across systems. If the results remain separate documents, the reader still has to join the customer history and establish which version applies. Ask whether the product resolves entities, understands changes over time and enforces the original permissions through every query path.

Markdown memory files and hand-built knowledge bases

Notes that an agent reads at the start of a session work well for a defined job. A growing team needs to decide who maintains them, how changes reach other agents and which notes each reader may see. Files can inherit folder permissions, but passages copied between files need their access and provenance preserved too. Loading the whole collection on every request also becomes expensive as it grows.

A fine-tuned model

Fine-tuning can teach a house format or a specialist task. Changing company facts need a separate record that can be updated, cited and permission-checked. In Oded Ovadia and colleagues' comparison of knowledge injection methods, retrieval outperformed unsupervised fine-tuning on the knowledge-intensive tasks they tested. That is evidence for the retrieval approach, rather than a verdict on every form of fine-tuning.

Information learned into shared weights has no built-in source-level access check for each person asking. Nor do those weights provide a reliable citation trail. We cover that distinction in What you own when you own your AI.

An assistant with connectors

Connecting an assistant to Slack, email and Drive gives it useful reach. The next questions are how it joins records across those systems, selects the current evidence and preserves access. The results depend on the connectors and retrieval design. A shared context layer can give several assistants the same maintained record instead of rebuilding it inside each conversation.

A vector database

Similarity search retrieves passages related to a question. A vector database is a useful part of that system. Entity matching, dates, permissions and evidence-linked write-back still need to be represented and enforced in the surrounding application.

A company brain can use all these components. Its value comes from how they work together: connected sources become a record of the business that people and agents can query and extend.

The Component And The Whole
Useful ForAn edited account of how the company works.
Ask About The System Around ItWho updates it after a decision in a meeting?
Identity · Dates · Access · Evidence · Write-back
Products combine these building blocks in different ways. Check the surrounding system rather than assuming a feature from its label.

The Sources

What goes in

A first use case often needs a handful of well-chosen sources.

  • Documents: SharePoint, OneDrive, Google Drive and Notion, including PDFs, presentations and spreadsheets.
  • Communication: email, calendars, Slack, Teams and WhatsApp where people choose to connect it.
  • Meetings: transcripts and notes from the conversations where decisions happen.
  • Business systems: the CRM, ticket tracker and code repository.
  • Licensed data: outside company information, stored and reused where the licence permits.
  • Finished work: findings, decisions and drafts written back with their evidence.

Agree freshness per source. A priority chat channel might need updates within minutes; an archive may refresh overnight. The connector and deployment determine what is possible. Measure the age of the evidence used in answers, alongside the health of the last sync.

Grant the access the use case needs. Start with the relevant folders, channels and accounts. Preserve source restrictions as the knowledge moves into the graph. A shared connector credential must not turn every retrieved passage into company-wide information.

Leave out the noise. Automated alerts and duplicated exports can dominate a retrieval result without adding much knowledge. Test source selection against real questions before assuming that another connector will improve the answers.

The company brain and the personal brain

Shared company knowledge and personal context need separate ownership rules. In our model, the company brain holds the agreed shared sources. A personal brain holds a person's private email, calendar, notes, direct messages and relationships. Company search does not read that private record.

A source can feed different scopes: shared Slack channels belong in the agreed company context, while direct messages belong to the person. Personal knowledge becomes shared only through the sharing rules the person chooses.

When someone leaves, the company retains the shared work it is entitled to keep. Private personal context stays separate. Agree retention, access removal and export arrangements during setup. Our permissions model explains that boundary in more detail.

Two Brains, Clear Ownership
Company Brain
Shared channels and documents
Meetings, tickets and CRM records
Source permissions on every passage
Personal Brain
Private email, notes and messages
Calendar and relationships
Company search has no access
Choose who receives a relationship signal:
The relationship stays in your personal brain. Company search cannot read it.
Illustrative sharing model. Shared company work and private personal context have separate access rules.

The Architecture

How one is built

The order of operations determines which claims the system can support. Follow one document from its source into an answer.

  1. Fetch permissions and dates with the text. Keep the source's modification time separate from ingestion time. Loading a 2012 deck today must not make it newer than the 2025 revision.
  2. Preserve the source passages. Split the text into addressable passages, keeping the file, position, version and access rules. Store model findings alongside that evidence so a citation can still lead back to the original text.
  3. Resolve entities. Match people, companies, projects and deals across systems using evidence beyond a similar name. Our fictional roll-up dataset includes one customer under four names and a separate lookalike. The published retrieval tests check whether a system joins the four and keeps the fifth apart.
  4. Build and review the ontology. An ontology describes the entities and relationships the use case needs. Generate a starting model from the sources, review it with the people doing the work and revise it as their questions change.
  5. Link facts and record change. Connect passages to the entities they describe. Extract commitments, decisions, blockers and scope changes. Keep the evidence and dates behind a replacement instead of silently overwriting the earlier account.
  6. Enrich the record. Attach licensed outside data to the right entity. Reuse it within its licence and refresh schedule, so repeated questions can avoid unnecessary vendor calls.
  7. Retrieve in stages. Apply access and source filters before returning evidence. Give the agent short excerpts and identifiers first, then fetch the full passages it needs. Graph traversal can connect a customer to its people, projects and decisions.
  8. Write back with evidence and approval. Store useful finished work with links to its sources. Separate an agent's proposed finding from an approved change to the shared record, and record who made that change.

Fetching, extraction and matching can often run on code or smaller models. Use more capable models where a task needs judgement. Measure quality and cost on your own archive before choosing the processing mix.

From Source To Answer
Read the pricing deck with its source date and access rules. Ingestion time is a separate field.
2012 deck + 2025 deck · Loaded today
An illustrative pricing-deck example. Walk through the eight steps to follow the evidence.

The Work

Answer, push, act and remember

Answer a question with evidence

People ask through the assistant or workspace they already use. The same company context can serve Claude, ChatGPT, a coding agent or a team workflow through an integration such as MCP. Each answer needs the sources and dates that support it. If the record cannot support an answer, say what was searched and what remains unknown.

Push the changes people need to see

A daily brief, a drafted stand-up or a meeting note can bring changes into view before two teams repeat the same work. One pilot uses the quality of its drafted stand-up as a practical test of context: how much must a person correct before sending it?

Give agents the context for an action

A proposal can start from a comparable project. An onboarding brief can draw on past configuration decisions. An introduction request can start with the colleague who has a useful relationship to the target. People approve what is sent or changed.

Remember useful finished work

An analyst's research can become the next person's starting point. An approved engineering decision can retain the customer conversation that prompted it. Each contribution needs ownership, sources and a way to correct or replace it later.

The same foundation supports consultancy proposals and precedents, investment research and the handover between sales and delivery. Sold, scoped, shipped follows that last workflow through a project.

Answer, Push, Act, Remember
Shared Company Brain
A colleague asks what pricing was agreed. The answer uses the current evidence their access permits.
A cited answer, with the source date
Each approved contribution can improve the context for the next task. Select a part of the loop.

Why Now

More AI work makes shared context more valuable

Coordination was expensive before AI. Atlassian's account of its 2025 State of Teams findings says roughly half of knowledge workers report teams unknowingly working on the same things. More parallel AI threads create more places for that work to diverge.

Faros AI's 2025 study of over 10,000 developers found that teams with high AI adoption completed 21% more tasks and merged 98% more pull requests, while review time rose 91%. It found no significant correlation with improvement at company level. These are observational findings. They show why individual output and company outcomes need to be measured separately.

Agents also pass work between tools and people. A shared record makes it possible to inspect what one agent told another, which evidence it used and whose access applied. Keeping that record outside model weights also makes it easier to change models while retaining company context.

The analyst research reflects the same concern. Forrester's October 2026 ContextOps article describes the operational work needed to govern, monitor and improve context. Gartner's 2027 trends announcement identifies AI context platforms and predicts accuracy and cost gains from better semantics. Those gains are a forecast, not a measured result from a 60x installation.

Repeated context assembly also has a cost. At $250 a research run, twice a working day for 21 days, the monthly total is $10,500. That is illustrative arithmetic. An audit has to establish how much of a real bill comes from work that could be reused, including the cost of maintaining the shared record. The $10,000 analyst sets out that test.

The Tests

Ten tests for a company brain

Run these on the system you are evaluating, including ours. Use questions whose answers you already know.

  1. Two people, one question. Sign in as people with different access. Where the evidence differs, the answers should reflect that difference.
  2. A source the asker cannot see. Ask about restricted material. Test direct search, graph traversal, saved answers and an agent using a shared credential. The restriction must hold through each route.
  3. The current version. Ask about a price, scope or decision that changed. Check the answer, source date and replacement history.
  4. An answer as of a date. Ask what was true before that change. Check that the system retrieves the earlier evidence and labels the time being answered.
  5. One customer, several names. Join the customer's records across systems. Include a lookalike company to test whether identity matching goes too far.
  6. A question the record cannot answer. Ask about work with no supporting evidence. The system should explain the gap and distinguish a nearby example from an answer.
  7. The passage behind each claim. Follow the citations. Check that the original passage supports the claim and that you may still open it.
  8. A source change. Edit a document or post an update. Measure when it appears in answers, and compare that with the agreed freshness for that source.
  9. A different model. Change the model behind an agent. Check that the context, access rules and history remain available.
  10. A complete export. Ask for the evidence, entity relationships, dates and permissions in a usable format. Test what you can query and run independently of the supplier.

Ask where each rule is enforced. Access checks must cover the evidence store and every route that retrieves from it. Demonstrate the failure cases with ordinary user accounts as well as an administrator.

Your Evaluation Checklist
0 of 10 reviewed
Tick a test after checking it on your installation. These are your review notes, not prefilled product results.

The Limits

What it cannot do for you

It cannot recover knowledge that was never recorded. Transcripts and chat can capture useful context, but some knowledge remains in people's heads. Interviews and human judgement still matter.

Recording changes behaviour. People may move a sensitive conversation when they think it will be shared too widely. Explain the ownership and sharing rules before connecting personal sources, and make those rules visible in the product.

Source permissions can already be wrong. A folder shared too widely needs fixing at the source. The brain must then pick up that correction and apply it to later retrieval.

It cannot settle a disagreement for the team. Two partners can read the same evidence and reach different conclusions. The brain helps them establish the facts and keep the decision they make. Leadership and responsibility stay with people.

The first load needs time and a budget. Processing a historical archive can cost more than the daily refreshes that follow. New sources, changed extraction rules and reprocessing can add further work. Include them when evaluating the running cost.

A First Use Case

Start with one expensive question

Choose a question your team spends too long answering. It determines which sources, relationships and quality checks the first version needs.

  1. Collect 20 to 30 real questions from the past month, with the answers a good colleague would give. Keep them as an evaluation set.
  2. Map the sources behind those answers, their owners and their access rules. Fix obvious access problems and leave out irrelevant noise.
  3. Agree a refresh interval for each source and a way to measure it.
  4. Review the entities and relationships with the people doing the work.
  5. Connect one team's existing assistant. Keep changes to shared records under review while the team learns to trust the answers.
  6. Ship a visible output, such as a daily brief or drafted stand-up, and measure its accuracy and the editing it needs.

We install an agreed first use case in two weeks. Choose 60x Cloud for hosting with EU or US data residency, or Your Cloud inside your Azure, AWS or GCP account. Both can run on open-weight models.

Book a demo and bring the question your team spends most time answering. We will work through the sources, permissions and evidence a useful answer needs.

Sources

Sources

  • Garry Tan, Every company should have a Brain, AI Engineer World's Fair 2026.
  • Gartner, Top Strategic Technology Trends for 2027, 20 October 2026.
  • Charlie Dai, Leslie Joseph and Indranil Bandyopadhyay, Context Engineering and ContextOps, Forrester, 19 October 2026.
  • Oded Ovadia, Menachem Brief, Moshik Mishaeli and Oren Elisha, Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs, revised January 2024.
  • Atlassian, How to make work visible and improve alignment, reporting its State of Teams 2025 findings.
  • Faros Research, The AI Productivity Paradox Report 2025.

Client examples are anonymised. The roll-up dataset and visual examples are fictional. The research cost calculation is illustrative. Deployment scope, integrations and refresh intervals are agreed for each installation.

Frequently asked questions

What is a company brain?

A company brain is a shared, permissioned and time-aware model of what a company knows. It connects the systems where work happens, joins information around business entities and gives people and AI agents evidence they can query and extend.

What is the difference between a company brain and RAG?

Retrieval-augmented generation supplies relevant external information to a model. A company brain can use RAG, while also maintaining entity relationships, source permissions, change history and approved work across the company. The useful distinction is which of those capabilities the implementation actually provides.

Can a company brain keep personal information private?

It can separate agreed company sources from private personal context and enforce access when evidence is retrieved. In 60x's model, company search does not read a person's private personal brain. Sharing from that personal context follows the person's chosen rules, and the installation must test those boundaries through every query route.

Related reading

  • A company brain that knows who is asking

    Two people can ask the same question and need different answers. A company brain should keep each answer inside the asker's permissions, for people and agents alike.

  • What you own when you own your AI

    Open weights make the model yours. Your company's context, and the tools your people use it through, make the AI yours.

  • How to become an AI-native company

    Build one company brain, then run routine work from it. Twenty automations, the order to build them in, and how to keep them working.

Author

Fergus McKenzie-Wilson

Fergus McKenzie-Wilson

Founder

Pioneered Multi-Agent AI in 2023, transforming a consultancy into AI-native SaaS. Serial entrepreneur and exited founder; co-founded Hydra Drones at university and exited after 4 years. Awarded an Innovate UK grant and received multiple innovation awards from the Austrian government. Fergus architects and leads the engineering of 60x's agentic infrastructure and proprietary Knowledge Graph design.

Want help turning a research thesis into a working system?

We build the software, workflows, and knowledge layers that make AI useful inside real operating teams.

Book a demo →Book a demo →
60x

We help enterprise leaders deliver AI outcomes.

Company BrainKnowledge GraphWhat We KnewPermissionsTrust
Private EquityFinancial ServicesConsultancies
AboutCase StudiesJobs
BlogContactTermsPrivacyCompanies House

Solutions

Company BrainKnowledge GraphWhat We KnewPermissionsTrust

Industries

Private EquityFinancial ServicesConsultancies

Company

AboutCase StudiesJobs

Resources

BlogContactTermsPrivacyCompanies House
Cyber Essentials Certified
Unicorn Mafia

© 2026 60x.ai. All rights reserved.

PrivacyTerms of Use