--- title: "Company Brain on SurrealDB: Ingest, Permissions and Time" description: "An interactive company brain on SurrealDB and Agent Memory: one pricing decision followed through ingest, per-person permissions and every earlier version." url: https://surrealdb.com/explore/company-brain --- # One brain, many askers. Current by default, with every earlier version kept. Company brain · interactive demo A company brain captures how an organisation works and serves it to people and agents alike. This demo follows one pricing decision at a fictional company, Acme, through three problems most attempts get wrong: consolidation, permissions and time. SurrealDB holds the graph and enforces access. SurrealDB Agent Memory, beside it, keeps every version and the reason it changed. Sources on the left feed a SurrealDB graph in the centre; Agent Memory on the right keeps every version. ## Six tools, one company ``` ``` Back Next For decision makers ## The model is no longer the bottleneck. The knowledge layer is. An agent quotes a customer last quarter’s pricing. A new hire spends two weeks reconstructing a decision that was made and then reversed a year earlier. An account manager leaves, and the relationship context leaves with them. None of these is a model failure. Each one happens because no single system holds what the company knows in a form that people and agents can both use. **95%** of generative AI pilots produced no measurable business return in MIT’s study of 300 public implementations. [MIT NANDA, 2025](https://www.healthcareitnews.com/news/mit-95-enterprise-ai-pilots-fail-deliver-measurable-roi) **40%+** of agentic AI projects will be cancelled by the end of 2027, on cost, unclear value and weak risk controls. [Gartner, 2025](https://www.gartner.com/en/newsroom/press-releases/2025-06-25-gartner-predicts-over-40-percent-of-agentic-ai-projects-will-be-canceled-by-end-of-2027) **93** apps run in the average company, so no one person or wiki holds the whole picture. [Okta, Businesses at Work](https://www.okta.com/reports/businesses-at-work/) **65%** more likely: staff at high-turnover companies call finding the information they need very difficult or nearly impossible. [Panopto, 2018](https://www.panopto.com/company/news/inefficient-knowledge-sharing-costs-large-businesses-47-million-per-year/) MIT’s diagnosis is a learning gap rather than a model gap: the tools do not learn how the organisation actually works. A person running a bad search loses ten minutes. An agent working from a bad retrieval takes a wrong action, writes it to a system of record and moves on at machine speed, and its answer looks just as confident as a correct one. Why most attempts fail ## Four failure modes that better retrieval cannot fix ### Entities blended together A search for Phoenix returns an engineering project, an HR programme and an office in Arizona. A model given all three writes one confident answer that mixes them. Consolidation keeps them apart. Shown in: Ingest and consolidate ### Permissions added afterwards A check on the parent document does not stop a semantic search from surfacing a sensitive paragraph out of context. The candidate set has to be secured before anything is ranked. Shown in: Ask as different people ### Freshness that nobody owns A vector index returns a stale fact with the same confidence as a current one, because nothing in it records when the fact stopped being true. Shown in: Travel in time ### Ranking in place of knowledge Reranking and hybrid search improve the order of results. They cannot tell a model what is current, what is authoritative or what is private. Those properties have to live in the data. Evidence at scale ## Meta reached 63,000 installs in three months Meta’s analytics organisation has published how it built an AI second brain for its knowledge workers. It went from zero to more than 63,000 installs and 10,000 daily users in three months, across engineering, product, design, legal, finance, communications and sales. It is the strongest public account in this space because it describes what shipped, what broke and what fixing it took. [Analytics at Meta, How we built an AI second brain for 60k knowledge workers](https://medium.com/@AnalyticsAtMeta/how-we-built-an-ai-second-brain-for-60k-knowledge-workers-78c507dd795b) ### Governed access came first Agents reach internal systems through authenticated, scoped MCP servers and CLIs. Meta treated that access as a prerequisite rather than a later addition. ### Context arrives in layers Context-window limits led to progressive disclosure: lean context by default, with detail pulled in only when a task needs it. ### Workflows became skills Versioned, markdown-defined skills such as `/start-project` turn company knowledge into something an agent can run. Y Combinator’s Summer 2026 [Request for Startups](https://www.ycombinator.com/rfs) lists the company brain as a category it wants to fund, on the same premise. ### The market agrees Glean, the closest public comparison, sells a permissions-aware layer over a company’s fragmented knowledge and has passed [$300M in annual recurring revenue](https://www.glean.com/press/glean-surpasses-300m-arr-unrivaled-enterprise-context-fuels-ai-adoption). Timing ## When a company brain pays off Industry matters less than how much decision context lives outside the systems of record, and how many agents need to share it. ### Strong fit - More than one AI agent in production, where the agents have to agree with each other. - Around 50 people or more, with knowledge spread across five or more tools. - Customer-facing teams whose relationship context lives in people and calls rather than CRM fields. - Regulated industries, where who knew what, and when, has to be answerable. ### Early A team of 15 is usually well served by lightweight ambient capture. The full architecture on this page is a different investment, sized for a larger problem. ### How to start 1. Scope one team, one workflow and one clear before and after. 2. Have agents write outcomes back from the pilot onwards, so the brain learns from its own use. 3. Settle the permission model before scaling ingestion. It is the most expensive part to retrofit. Beyond the demo ## What is still yours to build? The database is the substrate: one engine for records, graph, vectors, full-text and permissions. Three parts of a company brain sit above it. ### Connectors Getting events out of Slack, calls, Jira and a CRM, with their access lists intact. Budget weeks per source. ### Consolidation policy Which source is authoritative, and how confident a match must be before two mentions become one entity. ### Trust Ambient capture only works if people know what is captured and who can read it. [Read the SurrealDB Agent Memory docs](https://surrealdb.com/docs/agent-memory) ## Explore more - [**What is agent memory?** The three kinds of agent memory, what each one stores, and where it sits in an AI stack.](https://surrealdb.com/explore/what-is-agent-memory) - [**Financial services ontology** Eight source systems land in one SurrealDB graph, with the SurrealQL behind every entity and relation.](https://surrealdb.com/explore/financial-services-ontology)