A written method for one recurring video job: the order to make the calls in, which parts of the answer are measurements, and which parts are judgements that are yours to make. Your agent fetches one with get_playbook before it starts the work.

Why are playbooks not just part of the tool descriptions?

Because tool descriptions are paid for on every connection, and a playbook is paid for only by whoever asks. Everything permanent is about 2,600 tokens; the playbooks together are far more than that, and loading them into every session would tax every user for a method most of them will not use.

Can I use a playbook without an agent?

Yes. They are readable methods, and each one is published here in full. Nothing in them needs a model to run it. They are how a competent person does the job, written down.

Playbooks

A playbook is a method for one recurring job: the call order, what is measurable, and where the judgement is yours rather than ours. Your agent fetches one with get_playbook, and a client that supports MCP prompts shows them as commands you can pick from a list.

Last updated 31 August 2026

The playbooks

Each one is published here in full. The when column is the sentence an agent matches a request against, which is why it describes a situation rather than a document.

Available playbooks
Playbook	What it is for	When it applies
Take an ad apart	Break a performing ad into its beats and claims so the reusable part can be named	an ad or piece of marketing is to be taken apart, or called a winner and copied from
Turn a video into a prompt	Watch a video somebody wants to reproduce and write what to order from a generator	a video is to be remade, copied or matched, or somebody asks for the prompt behind a clip

Take an ad apartBreak a performing ad into its beats and claims so the reusable part can be named1,472 words
Turn a video into a promptWatch a video somebody wants to reproduce and write what to order from a generator1,511 words

Using one from an agent

Clients that support MCP prompts show these as commands, so a playbook can be picked before anybody has described their problem.

Fetch a method, then do the worktext

get_playbook(task: "ad-teardown")
watch_video(url: "https://www.facebook.com/ads/library/?id=1234567890")

Long playbooks are split into sections, fetched by name and only when asked for, with get_playbook(task, section). That keeps the first response small enough to be worth reading in full.

What a playbook will not do

The constraint that makes them worth following rather than just long.

The same rule runs through the engine itself: there is no is_music field and no hook_ends_at. Those are judgements, and hands you the evidence instead, along with the moment the number belongs to.

Questions

What is a playbook?: A written method for one recurring video job: the order to make the calls in, which parts of the answer are measurements, and which parts are judgements that are yours to make. Your agent fetches one with get_playbook before it starts the work.
Why are playbooks not just part of the tool descriptions?: Because tool descriptions are paid for on every connection, and a playbook is paid for only by whoever asks. Everything permanent is about 2,600 tokens; the playbooks together are far more than that, and loading them into every session would tax every user for a method most of them will not use.
Can I use a playbook without an agent?: Yes. They are readable methods, and each one is published here in full. Nothing in them needs a model to run it. They are how a competent person does the job, written down.