# Your company, in one brain

> Your company in one file your agents read. Interview loop, gated, 20 minutes.

Loop: `brain-build`
Category: Ops
Autonomy: auto+gate
License: MIT
Source: https://vibemarketers.ai/loops/brain-build

Builds the Brain, the single source of truth every other loop reads. Positioning, ICP, buyer questions, claims and proof, competitive intel, content history, voice.

## What you need

- none required

## Goal prompt

Give this to your agent. Replace anything in <angle brackets> with your own.

```
Build the Brain for <domain>. Read the site, the docs, and any exports in
/inputs. Write Brain/positioning.md, icp.md, buyer-questions.md,
claims-and-proof.md, competitive-intel.md, content-history.md, and voice.md.
Every claim in claims-and-proof.md names a source URL and a date.
```

## Verifier prompt

Run this as a second, separate agent. It grades the first one's work and must be
able to fail. A checker that never fails is not a checker.

```
Open every file in Brain/. FAIL if any file is missing, if any claim in
claims-and-proof.md has no source URL, if voice.md has no banned-word list,
or if any file contains an em dash. Otherwise PASS.
```

## Stopping condition

Seven Brain files exist, the verifier marks PASS, and a PR is open.

## How to run it

1. Save this file into your project, for example `.claude/loops/brain-build.md`.
2. Open your agent in that project (Claude Code, Cursor, or Codex).
3. Paste the goal prompt, with your own values in place of the angle brackets.
4. When it stops, start a fresh session and paste the verifier prompt.
5. Read the verdict before you accept any change.

## What happened when we ran it

Last run 2026-09-21 on vibemarketers.ai.

- Baseline: No Brain existed. Brain/ held one file, voice.md, written by hand during Goal 1. Every other loop started from an empty context and guessed at positioning.
- Result: 7 of 7 Brain files exist. 12 provable claims recorded, each with a source URL and a date, and 5 claims explicitly listed as unprovable until a named condition is met. The verifier failed the first pass: 3 claims cited a repo path rather than a resolvable URL. Fixed, then PASS.
- What this does not prove: This loop produces an input, not a marketing outcome. No citation or traffic movement is attributable to it. The Brain is built from two websites and the repo, not from sales calls or a CRM, so the buyer-questions file is inferred from published copy rather than observed in conversation.
- Cost: 1 human touch, 22 minutes, $0.00
- Raw log: https://github.com/genwfurukawa/vibemarketers-v2/blob/main/lab/runs/2026-09-21-brain-build.json

## Inside a company

- Problem it solves: Every agent task starts from a different idea of what the company is, so output drifts.
- Source of truth it reads: The Brain directory: positioning, ICP, buyer questions, claims and proof, competitive intel, content history, voice.
- What it may do: Read the website, the docs, the CRM export, and past content. Write Brain files. Open a PR.
- Who approves: One PR approval from the marketing lead before the Brain is used by any other loop.
- Who owns it: Head of marketing
- How you measure it: Share of downstream loop outputs that cite a Brain file instead of guessing.

MIT licensed. Copy it, change it, run it. No attribution required.