---
title: "How to build a company brain: where to start and what it costs"
description: "How to build a company brain: where to start, who should own it, where MCP fits, deployment models, hidden costs, and why permissions decide if it works."
url: https://surrealdb.com/blog/how-to-build-a-company-brain-where-to-start-and-what-it-costs
date: 2026-11-21
authors: "Martin Schaer"
---

# How to build a company brain: where to start and what it costs

![How to build a company brain: where to start and what it costs](https://cdn.surrealdb.com/2avdxy464do6ugigwpzq93ck.auto)

To build a company brain, start with one workflow where missing context hurts,
such as product and engineering alignment meetings. Capture those
conversations automatically, give them permissions that match who was in the
room, and serve them to the agents doing the follow-up work. Prove that one
use case, then add sources.

This is the practical follow-up to
[What is a company brain?](https://surrealdb.com/blog/what-is-a-company-brain).
That post covers the idea. This one covers the decisions: where to start, who
owns it, what to buy or build, and what it costs.

## Is a company brain the same as a context layer?

No. A context layer gives agents access to data that is already recorded and
structured: the CRM, the data warehouse, policy documents. A company brain
adds what was never written down: what was decided on a call, why it was
decided in a chat thread, what a client said in passing.

| | Context layer | Enterprise search | Company brain |
| :-- | :-- | :-- | :-- |
| **What it holds** | Structured data you already store | Documents and messages across your apps | Decisions, reasons and commitments, including from calls and private chats |
| **How it learns** | When someone updates a system | When a document changes | Continuously, from everyday work |
| **Who uses it** | Agents | People | People and agents |
| **Hardest problem** | Data quality | Relevance | Permissions on private conversations |

Most organisations need both. The context layer tells an agent what the
records say. The company brain tells it why.

## Where should you start building a company brain?

Start with a quick win that has a clear benefit for the business. The trap is
designing an organisation-wide system on day one. You learn more from one working use case
than from months of planning, and that learning shapes the next step.

My recommendation is to start as if you were deploying a fleet of notetakers.
Picture a product manager and two engineers discussing a feature on a call.
Today, the coding agent that later picks up that ticket knows none of it. With
a company brain, it automatically gets the decisions, the constraints and the
reasons from that meeting. For the people involved, that feels like a
superpower.

A sequence that works:

1. **Pick one recurring meeting** where decisions get made and work follows,
   such as product and engineering alignment.
2. **Capture it automatically**, with the people in the room knowing what is
   captured and who can see it.
3. **Scope each memory to its participants and their teams**, so access matches
   who was there.
4. **Serve it to the agents doing the follow-up work**, starting with coding
   agents.
5. **Add the sources that record the outcome**, such as tickets and product
   requirement documents, so the brain knows what was decided and what was
   delivered.
6. **Move to the next workflow** where context nobody could reach before would
   change how people work.

Engineering is a good first partner. Engineers tend to use AI the most, their
agents benefit immediately, and they often arrive with ideas of their own.

## Who should own a company brain?

A business unit or a dedicated role with a broad view of the business should
own it. It is a company-wide asset, and its owner needs to understand where
the business value is. Pair that owner closely with engineering, which will build most of the
integrations and is usually the first team to benefit.

## What is the tech stack for a company brain?

A company brain has four layers. You can buy, build or assemble each one
separately.

- **Capture:** connectors that pull in meetings, chats, tickets and documents.
  This is where most of the custom work goes.
- **Understanding:** turning raw transcripts and files into facts, people,
  decisions and relationships, and reconciling them when they contradict each
  other.
- **Memory:** the database that stores all of it, finds it by meaning, by
  keyword and by relationship, and enforces who can see what.
- **Serving:** the interface agents and people use to ask questions, usually
  through MCP or a native integration.

The memory layer is the one to choose most carefully. It holds the private
data and enforces the permissions, and replacing it later means migrating
everything.

## What does MCP have to do with a company brain?

MCP (Model Context Protocol) is the plug, not the brain. It is an open
standard that lets any AI agent connect to a tool or data source in the same
way. That makes it a fast way to connect your company brain to Claude,
ChatGPT, coding agents and internal assistants without building each
integration by hand.

Storing knowledge and deciding who may see it are jobs for the memory layer
underneath. Two more points matter when you
plan:

- **MCP is not the only protocol.** Agents can also reach data through APIs,
  command-line tools and native integrations.
- **Native plugs can be cheaper.** A purpose-built integration is often faster
  and uses fewer tokens than a generic MCP server, which adds up when
  thousands of agent calls run every day.

Use MCP to move fast, and switch to a native integration where volume makes
the token bill matter.

## Should you build, buy or assemble?

Assemble. Off-the-shelf work AI such as Glean or Microsoft Copilot covers
search across popular apps well. It reaches its limits where your knowledge
lives in internal tools, private conversations and workflows nobody else has.

Most of the effort goes into integrations that have to be custom-made. This is
why forward-deployed engineers, who build inside the customer's organisation,
have become so common. AI has also made building much cheaper than it was. The
sweet spot is to keep the tools your teams already use and build the bridges
between them, on top of a memory layer you control.

## What should you evaluate?

Most buyers are still working this out, and they are right to be cautious.
These questions separate a demo from something you can run:

- **Permissions:** are they enforced inside every search, or applied
  afterwards by the application?
- **Deployment:** does it run where your data rules require?
- **Cost:** what does a sample of your own content cost per page and per
  query?
- **Freshness:** can it tell a reversed decision from a current one?
- **Integrations:** does it connect to the tools your teams actually use?
- **Exit:** how hard is it to move your memory somewhere else later?

## Which deployment model should you choose?

It depends on how regulated you are.

| Model | Best for | Trade-off |
| :-- | :-- | :-- |
| **SaaS or managed cloud** | Companies without strict data rules | Easiest and cheapest to run |
| **Bring your own cloud (BYOC)** | Companies that need data in their own cloud account | More control, more operational work |
| **On-premises** | Banks, healthcare, government | Full control, highest cost |

A company brain holds your most sensitive conversations, so involve legal and
security early. Settle the deployment model before you choose vendors,
because it rules some of them out.

## How much does a company brain cost?

The cost depends on how many sources you connect, how complex your
permissions are, and how much content you process. Published estimates for
custom enterprise search, the closest comparable, range from $40,000 to
$200,000 and 12 to 24 months to build
([RaftLabs](https://www.raftlabs.com/blog/cost-to-build-enterprise-search-software),
[GoSearch](https://www.gosearch.ai/blog/how-much-does-enterprise-search-cost/),
both vendors, 2026).

The main cost drivers:

- **Connectors.** One SharePoint connector with nested folder permissions can
  take three to five weeks and 30 to 40% of the project timeline, according to
  GoSearch.
- **Document processing.** Turning PDFs, slides and transcripts into usable
  text, at a price per page.
- **Model and token usage.** Every question an agent asks costs tokens, and
  agents ask a lot.
- **People's time.** Someone has to own sources, settle conflicts and review
  what the brain gets wrong.

### What are the hidden costs?

The hidden costs are the choices that look small at the start. I saw one
company building a context layer spend its whole budget on document
ingestion. It picked the most accurate document parser available, which cost
at least 30 times more per page than a standard one. Nobody had compared cost
against accuracy, or looked at hybrid methods that don't run everything on
GPUs.

Other costs that tend to surprise teams:

- **Re-processing.** Changing your AI model or parser can mean processing
  everything again.
- **Permission syncing.** Keeping access in step with your identity system as
  people join, move and leave.
- **Legal and privacy review**, especially for recorded calls.
- **Change management.** Explaining to employees what is captured, and earning
  their trust.

Run a small sample through two or three options before committing to any
per-page or per-token price at scale.

## Why do most company brain projects fail?

Most fail on permissions and governance. Recorded conversations
mix information with different audiences. When a team can't enforce access
per conversation, the safe choice is to include only what everyone may see.
The result is a brain built to the lowest common level of access. It misses
exactly the private context that made it worth building.

The wider numbers point the same way. MIT's NANDA initiative found that 95% of
generative AI pilots delivered no measurable return, and blamed tools that
don't learn from real workflows
([MIT NANDA, July 2025](https://www.healthcareitnews.com/news/mit-95-enterprise-ai-pilots-fail-deliver-measurable-roi)).
Gartner predicts that over 40% of agentic AI projects will be cancelled by the
end of 2027, citing costs, unclear value and weak risk controls
([Gartner, June 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)).

The other common causes:

- **Starting too big**, so nothing reaches users before the budget runs out.
- **No clear business benefit**, so nobody defends the project when priorities
  change.
- **Stale answers**, when the brain can't tell a reversed decision from a
  current one.

## Where does SurrealDB fit?

SurrealDB is the memory layer. It keeps documents, relationships, vector
search and full-text search in one database, so an agent can find a memory by
meaning, follow it to the people and decisions it relates to, and filter by
date in one request. Permissions are checked inside every search, on every
record, so a forgotten filter in an application can't leak a private
conversation.

[SurrealDB Agent Memory](https://surrealdb.com/docs/agent-memory/mental-model/contexts-and-scope)
builds on that to ingest conversations and serve them to agents. Each memory
is scoped to the people it belongs to, and an agent can never see more than
the person it works for, and agents can reach it through MCP. SurrealDB itself
runs as a managed service, in your own cloud or on-premises.

That is what makes the notetaker approach safe. A product meeting stays with
the people who were in it and their team, and their coding agents can still
use it.

## Frequently asked questions

### How long does it take to build a company brain?

A single use case is much faster than an organisation-wide brain. Comparable
enterprise search projects built from scratch quote 12 to 24 months.

### Is a company brain the same as RAG?

RAG is a technique for feeding retrieved text to a model. A company brain uses
retrieval, but also captures knowledge continuously, reconciles
contradictions and enforces who can see what.

### What data should a company brain start with?

Meeting transcripts from one recurring decision-making meeting, then the
tickets and documents that record what came out of it.

## Get started

If you're planning a company brain, our solutions engineers can help you pick
the first use case and the right deployment model:

- [Book an exploration call with a solutions engineer](https://surrealdb.com/contact?content=Hi%2C%20I%20read%20your%20guide%20on%20how%20to%20build%20a%20company%20brain.%20We%27re%20exploring%20one%20for%20our%20organisation%20and%20would%20like%20to%20book%20an%20exploration%20call%20with%20a%20solutions%20engineer.)
- [See how teams use SurrealDB](https://surrealdb.com/solutions)
- [Read our whitepapers](https://surrealdb.com/whitepapers)
