Write it once · any agent, any project, any machine runs it · never pruned


Your agent draws the map of your whole system. Every session after loads it.

A playbook is a procedure written once — the deploy, the translation run, the weekly report — and run by any of your agents, in any project, on any machine, the same way every time. Notes carry the handover from one session to the next. And the atlas is what playbooks make possible: your agent draws the map of your whole system, from the code and the live system, and every session after opens with it.

Free plan · $0 · playbooks and notes on every plan

Write a procedure once. Every agent runs it.

A playbook is plain markdown: headings for the stages, fenced blocks for the commands, what to read back afterwards to know it worked. It is stored for your whole account, not for one project — your projects stay separate, your procedures are shared. Any agent fetches it and runs it in its own harness. Say "save this as a playbook" and it is one. Say "use playbook deploy" and it runs — and usually you don't even have to: a prompt whose words match a playbook gets it handed to the agent before it starts answering.

Never pruned

Curated records hold the current truth and get tidied as it moves on. A playbook holds how, and nobody prunes a procedure. The md file you wrote about the deploy rotted the first time a wire changed and nobody opened it again — a playbook is opened by the agent that is about to run it, every time. A recipe that took a week to find stays exactly as it was found.

The same way, everywhere

Five agents on one project, or one agent on five machines — the deploy is the same deploy. What you learned once about a run, every run knows from then on.

📋

Written the way you'd hand it to a colleague

The steps, the exact commands, what to check afterwards, what went wrong last time and when. Your agent adds what it learns running it, in the same session.

Notes — the handover

Where a session stopped, what is live, what comes next — written by your agent, kept per project, the last five always at hand. The next session opens with it. Start the PC, say "continue," and it carries on.

The atlas: a map of your whole system, kept true

The atlas is a playbook that teaches your agent how to map a project — and the map it draws is itself a playbook, so every session can open it. One root map per project: the boxes, the wires and what travels on them, the stores, and an index of plates. Four to eight plates, one per plane of the system, with the procedures inside the plate they belong to. Your agent reads the code and the live system and verifies every wire before it writes a line of the map.

The three rules of a map

  • Topology is drawn once, in the root. A plate never restates the wires; it carries only its own detail and its procedures. Duplication is where drift starts, so there is none by construction.
  • Values live nowhere in the map. No ports, caps, prices or counts — a page says where the number lives, never what it is. A map that carries values is wrong within a week.
  • Whoever changes a wire updates the map in the same session. The root carries a line — verified <date> against <what> — and a reader trusts the map exactly that far.

What the root map holds, in order

  • What the project is, in two sentences, and the verified line.
  • The diagram: boxes and arrows, one arrow per wire with what travels on it. Direction matters more than anything else on the page.
  • The wires, listed: who initiates, what travels, what never travels. This is the section that catches the lies.
  • The stores: every place state lives, what it holds, what it never holds.
  • The index: each plate by name, each procedure by plate and section.

What a plate holds

  • For each part of its plane: what it is, what it holds, what it talks to and in which direction, what it never does, and what happens when it runs.
  • Where the values live — pointers, never values.
  • Its procedures: the exact commands, what to read back to know it worked, and what has actually gone wrong doing it, with the date.

On a Tuesday, your agent opens the map, sees the wire it is about to touch, and checks the date on the verified line before it changes anything.

my-app-map — verified 2026-09-04 against commit a1b2c3d and the live containers

  browser ──(requests, session cookie)──▶ api ──(SQL)──▶ postgres
                                          │
                                          └──(jobs)──▶ worker ──(files)──▶ object store

Wires: the browser never talks to the worker; the worker never reads a cookie.
Stores: postgres (users, orders — never card numbers) · object store (uploads).
Plates: my-app-map-api · my-app-map-worker · my-app-map-data · my-app-map-ops
Procedures: deploy → my-app-map-ops, deploy · restore → my-app-map-data, restore

One sentence to your agent

The atlas method ships with your memory — it is in your playbooks from the first session. Mapping a project is one sentence, and the map's own last step makes sure every future session knows the map is there.

1 · already there

The methods ship with your memory

atlas, plan and prospectus are in your playbooks from the first session, on both editions. They are yours: edit one and it stays as you left it. Your agent offers them when a project has none yet.

2 · per project

Have the map drawn

In the project, tell your agent: use playbook atlas to write the map of this project. It reads the code and the live system, verifies every wire, and writes the root map and its plates.

3 · done by the method

The project learns it has a map

The method's last step saves a rule for the project: where its map lives, read it before changing a wire, update it in the same session. Every session from now on opens knowing the map is there.

Playbooks, notes and the atlas are on every plan, including the free one. Get started free

The plan: what the project intends, and why

The atlas says how a project works. The plan says what you meant to do with it. One playbook per project, four sections, and one law that keeps it honest: finished means gone. Its first lines open every session beside the notes, so the next session picks up the top one.

Four sections, and nothing else

  • Decided — one line per decision in force: the date, who decided, and the why. A proposal is never written as decided.
  • Next — ordered, ten items at most. Each line names the thing and says what finished looks like. Order is the only status a plan has.
  • Parked — ideas raised and not decided, each with the date it was raised.
  • Open with the human — the decisions only a person can make, one line each, dated.

The law that keeps it from rotting

  • Finished means gone. Whoever finishes an item removes it in the same session and puts what changed where it belongs: the wire in the atlas, the decision or the measurement in a record, the code in a commit. There is no Done section.
  • The Ledger is walked into it. A caught row that still matters becomes one line in Next or Parked and leaves the Ledger; the rest dies.
  • One writer at a time. Read the plan before rewriting it, and rewrite it whole.
my-app-plan — walked 2026-09-10 by the Tuesday session

## Decided
2026-08-14 · you · Postgres, not SQLite — two writers, one box
2026-09-02 · you · ship the importer before the dashboard — nobody can try it empty

## Next
1. Importer accepts CSV with a header row. Finished: a real customer file lands.
2. Retry the webhook on 5xx. Finished: one blip stops costing a record.
3. Dashboard: one chart, last 30 days. Finished: it answers "is it working".

## Parked
2026-08-30 · a public status page — nothing to show yet

## Open with your user
2026-09-08 · free tier: how many rows before it asks for money

One sentence to your agent

The plan method ships with your memory, like the atlas. Any project can keep one.

1 · already there

The method is in your playbooks

plan ships with every memory, from the first session. Edit it and it stays yours.

2 · per project

Have the plan written

In the project, tell your agent: use playbook plan to write the plan of this project. It seeds Decided from the decisions already in force, and Next from the notes and the Ledger.

3 · every session after

It opens with the work

The plan's first Next lines arrive with the session brief, beside the notes. A session starts by knowing what it is for.

The sheet: what a product promises

Hear it when it ships

New releases, real benchmarks and the occasional deep-dive. No spam, unsubscribe in one click.

Everything we build

External:   YouTube · GitHub