Open items live on the Q register — nothing here ships while its question is open.

• Week 3, day 5 · THE QA FLEET'S FIRST LIVE RUN — 18/18 verdicts, and the catch that proves the system. Three independent verifier agents per draft swept the six launch drafts in parallel — eighteen fresh-context verdicts, every one returned. The headline catch: a customer-facing “48-hour executive response” commitment that appears in no approved source anywhere. Serial human review had read past it three times; the fleet flagged it in one pass, with line numbers. Also caught: production notes sitting in shippable copy, and two superlatives inherited from a strategy doc that legal never cleared. Same day, the engine audited the brain itself and found two stale rules — fixed within hours.
• Week 3, day 4 · THE SEND-READY LIBRARY FILED — seven launch pieces, every one gated. Every drafted launch piece now lives in one governed folder: the all-staff email, two customer letters, the nurture sequence, the press release draft, the rep talk track, and the vendor letter. Each carries its approval state and the open questions blocking it. Nothing sends until its gates clear and a human promotes it.
• Week 3, day 2 · THE AGENT TEAM SHIPPED — 45 slash-activated specialists across nine departments. The brain now carries a named team, and every one of them publishes the single thing it refuses to do. 19 are running, 7 are built but have never been run, 10 are staged on real gates, 7 are buildable and 2 are blocked on a named dependency. The header, this entry and the roster are all counted from the same list, because they disagreed once and that is exactly the defect /audit exists to catch. Every agent spawns with fresh context and inherits the constitution — a worker that never read the rules is a leak vector.
• Week 2, day 5 · THE BRAND OS v3.0 ATLAS — the leadership-ready cut. The identity delivered as a complete working system: six named colours with printed reasons and the ratio each was measured at, the derived formulas beneath them, one owned motion and its flat fallback, and the mark redrawn once per size it has to survive rather than scaled. Dual view: Presentation for people, Full Spec for the machine. Everything marked PROPOSED until leadership locks it.
• Week 2, day 4 · THE WORK ZONE LIFECYCLE — position in the tree IS approval status. Eight personal zones, five folders each: My Space, Active Projects, Send for Approval, Save for Later, Archived. Work moves forward by moving folders; nothing ships from anywhere but Approved, and only a human moves it there. The review queue feeds the owner-approver chain, and nothing is ever deleted.
• Week 2, day 3 · THE FACT LAYER CLOSED — every number now has exactly one home. Pricing claims come from one authority file; capability claims from another. Anything the library doesn’t hold is UNKNOWN by rule and files itself as a numbered question instead of a guess. The distilled-meeting format landed the kickoff and brand-review sessions the same day.
• Week 2, day 1 · THE OPERATING LOOP WENT LIVE — seven steps, no shortcuts. Ask → Enhance → Route → Ground → Build → Scan → Approve. The prompt-enhancer scores thin requests and asks two or three sharp questions; the constitution’s routing table opens exactly the right rules; the scanner gates every deliverable with an exit code, not an opinion. First full pass ran clean on the welcome-letter draft.
• Week 1, day 4 · THE CONSTITUTION SHIPPED — ten hard rules the AI cannot break. The brain’s CLAUDE.md landed: identity, load order, the routing table, the trust order (Approved › Facts › Work Zone › everything else = UNKNOWN), ten hard rules, the output checklist, and the approval roster. A generated mirror serves any other AI the team points at the library.
• Week 1, day 2 · THE SKELETON STOOD UP — zones, registers, and the changelog rule. The six-zone tree went in place with the registers that keep it honest: the decisions log, the question ledger, the work log, and this changelog. The rule that makes it all work: nothing ships without a line here.
• Week 1, day 1 · THE KICKOFF — the brain gets its charter. Scope agreed with the demo client: one governed library the AI reads before it writes a word, guardrails that survive turnover, and production work done alongside the team. Two-week standup to a working brain; the dated plan went on the calendar the same afternoon.

Demo note. Everything on this page is demo content, and names marked * are demo placeholders, not real people.

What this is

The company brain is the team’s shared system: one library that holds what is true, how we sound, and what is approved, plus an AI that works inside it like a colleague. It lives in three connected places that always agree: the file library (plain files and folders — host them wherever the team already lives: SharePoint, OneDrive, Google Drive, Dropbox, Box, or a GitHub repo), the team site (the readable, browsable version of everything), and the AI (connected to the folder). You save work into it, the brain checks and files it, and the site updates so everyone sees the same truth.

This one document replaces the usual stack of guides. If something is not answered here, ask on the Team Questions page and the answer becomes part of the brain.

Access levels

Access is deliberately simple: everyone can read everything, you can only write in your own space, and one admin runs the machinery.

Folder-level permissions enforce this on whichever platform hosts the library. Until every level is wired, the working rule is the same: edit only inside your own Work Zone; everything else is read-only by convention.

Getting connected

1. The brain is just files and folders, so it lives happily on SharePoint, OneDrive, Google Drive, Dropbox, Box, or GitHub — whichever the company already uses. This demo assumes a synced cloud folder.
2. Sync it locally with that platform’s own tool (Sync / “Available offline” / clone), and pin it so it is always on your device.
3. That folder IS the brain. Anything you save inside it is in the library seconds later; anything a teammate saves appears for you the same way. No uploading, no emailing files.

Where things live

Your Work Zone

Five folders, and that is the entire system: 00 My Space (yours, no rules) · 01 Active Projects · 02 Send for Approval · 03 Save for Later · 04 Archived. Drop finished work into Send for Approval; Jordan*, Avery*, or Morgan* reviews it; approved work gets built into the brain and appears on the site, and anything needing changes comes back to your Active Projects with a note. Nothing is ever deleted, it retires to Archived.

The rules that keep the brain honest

1. Launch-gated above all — drafts and launch material stay internal until the launch date; the scanner enforces it.
2. Nothing invented — the brain never guesses; unknowns become numbered questions on the Team Questions page. You should work the same way.
3. Approved is sacred — never edit anything in the Approved library directly; changes go through the Work Zone and re-approval.
4. Markdown is canonical — every document’s .md is the source of truth; the styled page beside it regenerates automatically. Edit the .md, never the .html.
5. Ask, don’t assume — the Questions page routes every open item to its owner, and answers take effect the day they arrive.

Who to ask

Jordan Vale* — operator, AI owner, access, anything technical. Avery Kellen* — marketing lead, approvals, priorities. Everything else: the Team Questions page on the site.

The AI side of the brain. Connected to the library, the AI answers from filed facts with citations, drafts in the house voice, checks work before approval, and runs the machinery. This demo runs on Claude; the library also generates AGENTS.md, a universal mirror of the constitution, so ChatGPT, Gemini, Copilot, or any other tool the team prefers inherits the identical rules.

Connecting your AI to the brain

• The rule that makes everything work: point the AI at the synced brain folder. Once it can see the folder, the constitution loads automatically and it follows the house rules (no inventing, approved sources only, launch gates).
• Claude Code (the deep surface in this demo): open a session AT the brain folder — on Mac, open Terminal, cd into the brain folder, then claude. This is where the agents and skills live.
• Claude Desktop / Cowork: attach the brain folder and work conversationally while the AI reads and writes the actual files.
• Chat surfaces (claude.ai, chatgpt.com, gemini.google.com): no folder access by default — fine for general thinking, but brain questions belong in a connected surface so answers come from the filed truth, not memory.
• Bringing a different AI? Point it at the same folder and have it read AGENTS.md first — the rules travel with the library, not with any one tool.

The three surfaces, when to use which (this demo’s stack)

The agents (in a Code session at the brain root)

Type the slash command, add your request, press enter. Each specialist runs with fresh eyes and reports back. The full roster with examples is the site’s Agents tab, and every specialist ships real work — browse example outputs ↗. The daily four:

• /facts — ask anything; sourced answers with file citations, never guesses.
• /proof — verdict on any draft before it goes to Jordan* or Avery* (facts, voice, rules, the scanner).
• /draft — a new piece the brain’s way: right template, right tone, saved to your Work Zone.
• /revoice — rewrites existing copy into the approved voice.

The skills

Skills are packaged abilities: you do not type commands, you just ask for the thing (“scan this file”, “build the deck in the Mercado* style”, “clean up the BioSummit folder”) and the brain routes to the right skill. The full library with what each does is the site’s Skills tab. Fourteen generation skills are built and switch on automatically at brand-lock.

Models: which brain to rent

The table shows Claude’s lineup, the demo’s stack — pick the equivalent tier in whichever AI the team runs.

Effort levels

Some surfaces let you set how hard the model thinks: Low answers fast with minimal deliberation (lookups, formatting); Medium is the default balance; High reasons deeply before answering (analysis, plans, anything with edge cases). Rule of thumb: raise the effort when being wrong is expensive, lower it when speed matters more than polish.

The habits that make the AI useful here

1. Give it the file, not a description of the file. A connected AI reads the real thing.
2. Ask for sources. A brain answer should cite where the fact lives; if it cannot, the answer belongs on the Questions page.
3. Let it check your work — /proof before anything goes up the chain costs one minute and catches what tired eyes miss.
4. Save into your Work Zone and let the approval flow move it; never ask the AI to write into the Approved library directly (it will refuse anyway).
5. When the AI says UNKNOWN, that is the system working. File the question rather than pushing for a guess.

The short version

1. A real brain, in production. The original runs a live engagement: same architecture, same agents, same gates — with a real company’s facts inside.
2. A full duplicate, kept local. The copy never touched a public URL while it still held client material; it ran on a local server the whole way.
3. De-branded page by page. Every company, partner, and person was mapped to a demo replacement — same shape, zero real data. Names on prose carry an asterisk; the fictional client is Apex Instruments*, mid-rebrand, its new brand still an open {{slot}}.
4. The deep pass. 600+ library files were content-scrubbed in place; anything a rename couldn’t make safe — transcripts, price data, source binaries — was neutralized and unlinked, marked Not in demo right in the tree.
5. Gates, not vibes. Every pass ended with scrub-gate greps across every file, link crawls, and console checks. A clean-looking page that fails a gate doesn’t ship — the demo was built under the same rule it demonstrates.

What’s real vs what’s demo

The tooling

Built and de-branded in Claude Code sessions — the same operator surface the brain teaches — with scripted map passes for the sweeps and hand editing for everything with judgment in it. The full change log is on the changelog, demo-formatted like everything else.