Skip to main content

In one sentence

A playbook describes an outcome-driven conversation in plain language. Instead of drawing a flow chart with every branch, or stuffing everything into one prompt, you write checkpoints - the things that must be true before the conversation moves on.
New here? Read Why playbooks first - it explains the problem playbooks solve versus prompt-based and graph-based agents.

Checkpoints gate outcomes, not utterances

The engine decides what to say each turn. The checkpoints decide when the conversation is allowed to move on. You describe the destination; you do not script every sentence.
Example checkpoint
That is the whole mental model: checkpoints gate outcomes, not utterances.

The parts of a playbook

A small, complete playbook

How it runs: Talker + Director

A playbook is fast because two roles run at once:

Talker

Streams every spoken reply the moment it can, so the caller hears a natural, immediate response - no waiting on bookkeeping.

Director

Runs asynchronously: reads the transcript, extracts slot data, judges whether a checkpoint’s done_when is met, and runs any tools - over an event-sourced log.

The full checkpoint model

Go deeper on done_when / advance_when, slots, and interrupts in the mental-model guide.

Where playbooks come from

You rarely hand-write the YAML from scratch. You author a playbook by talking to a builder agent in the Playground - describe the job, and it writes the checkpoints for you.

What is the Playground

The browser app where you author, test, optimize, and ship a playbook.

Build an agent playbook

The hands-on walkthrough: describe an agent and watch its playbook appear.