Playbooks
A playbook here is a repeatable procedure, not a tutorial. Each one assumes you know the engineering; it specifies only what changes when an agent does the typing: the exact prompts to issue, the order to issue them in, the points where a human must look before the work continues, and the failure modes specific to that workflow. You should be able to open a playbook mid-incident, copy the prompts, and run it.
Every playbook follows the same skeleton — Objective, When to use, Inputs, Step-by-step process with prompts inline, Human review points, Expected artifacts, Common failures, Recovery, Acceptance criteria — so once you've run one, you can run any of them.
Which playbook?
Click through: Idea to Spec · New Project · MVP Build · Add a Feature · Large Tasks · Production Debugging · Recovery · Legacy Refactor · Migration.
Two playbooks sit outside the tree because they apply to everything the agent produces: Testing AI Code and Reviewing AI PRs. Run them regardless of which branch you took.
All playbooks
| Playbook | Objective | Risk | Typical duration |
|---|---|---|---|
| New Project | Stand up a repo with governing docs and quality gates before any feature | Low | Half a day |
| Idea to Spec | Turn a rough idea into ordered, session-sized, verifiable specs | Low | 1–3 hours |
| MVP Build | Ship an MVP as verified vertical slices on a walking skeleton | Medium | 1–3 weeks |
| Add a Feature | Add a feature to a production codebase without collateral damage | Medium | 2 hours–2 days |
| Legacy Refactor | Restructure legacy code with a behavior-change budget of zero | High | Days–weeks |
| Production Debugging | Diagnose and fix a live issue with the agent as investigator | High | 30 min–hours |
| Migration | Move stack, framework, or data store with verified equivalence | High | Days–weeks |
| Testing AI Code | Verify agent output against intent, not against the agent's own tests | Medium | 1–2 hours per feature |
| Reviewing AI PRs | Review high-volume AI diffs for behavior, not craftsmanship | Medium | 20–60 min per PR |
| Large Tasks | Execute work too big for one context window across sessions | Medium | Multiple days |
| Recovery | Get back to a known-good state after an agent session goes wrong | High | 1–4 hours |
Builder/reviewer splits, parallel agents, and other multi-agent workflows are not playbooks here — they live in Multi-Agent Patterns.
Related
- Prompts vs Specs — why every playbook routes through a written spec instead of a chat message.
- Responsibility Split — which decisions playbooks reserve for the human, and why.
- Prompt Library — the standalone prompt collection the playbooks draw from.
- Multi-Agent Patterns — builder/reviewer and parallel-agent workflows that compose with these playbooks.
- Case Studies — the playbooks executed end-to-end on realistic projects, mistakes included.