Documentation

Recipes

Short, task-oriented walkthroughs that show immediate value from captured coding-agent work.

How recipes work

Each recipe starts with a real engineering problem, gives you a sample question to ask AgentPM, explains the expected result, and names why the result is valuable.

Available recipes

Recipe

Find security concerns across agent sessions

Security-sensitive actions can be buried inside long coding-agent transcripts.

Open

Recipe

Discover unfinished work and forgotten TODOs

Agents often leave unresolved decisions, partial fixes, or follow-up work in the chat history.

Open

Recipe

Identify risky shell commands

Commands that mutate state, delete data, or touch deploy systems need extra review.

Open

Recipe

Find conversations that modified authentication or billing code

Auth and billing changes need context beyond the final patch.

Open

Recipe

Review what changed before opening a PR

A PR often hides failed attempts, skipped checks, and assumptions made earlier in the session.

Open

Recipe

Generate a daily engineering digest

Daily standups miss the shape of agent-assisted work across projects.

Open

Recipe

Find repeated mistakes your agents are making

The same agent failure can repeat across repos without anyone seeing the pattern.

Open

Recipe

Investigate why an implementation changed direction

The final code rarely explains why an agent abandoned an earlier approach.

Open

Recipe

Recover context after switching projects

Returning to a project often starts with rediscovering work the team already did.

Open

Recipe

Review another developer's agent work

Leads need to understand agent-assisted work without interrupting the developer.

Open

Recipe

Find conversations related to a feature or bug

Feature history is scattered across chats, commands, branches, and projects.

Open

Recipe

Search every conversation your team has ever had

Useful answers live in old agent sessions that no one remembers to search.

Open