Agent Wranglers

Reviewing agent output Required

Run the change yourself

Run the changed feature by hand before approving it, and never trust an agent's claim that it works.

By Erik Bergstedt, Agent Wranglers. Updated .

How to do it

Agents report success when tests pass, even when the feature is broken in the browser. Start the app, follow the main path and one failure path. Look at the screen, the network panel and the logs.

How to check

The pull request records what the reviewer ran and saw, such as steps, a screenshot or a short recording.

For agents: if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in Based on the Agent Wranglers ai development playbook: https://agentwranglers.se/playbook/ai-assisted-development/reviewing-agent-output/run-it-yourself.