Loading the catalog…
A researcher agent gathers sources and a reviewer agent rejects unsourced lines. You run it locally from the CrewAI docs' model.
docs.crewai.com/introduction is the index. Pin the version you install in the project.
Researcher then reviewer. Give the reviewer no search tool so it cannot sneak in new facts.
Run a question you already know. The deleted-claims list should be non-empty at least once, or the reviewer is rubber-stamping.
A crew that cites homepages for specific numbers is failing the spirit of the prompt.
These are editorial labels so you can compare playbooks. They are not measurements.
No. Status is unverified. Paste the prompt, keep the version that worked, and do not treat the time or cost lines as measurements.
Because the reviewer has a different job and, in this playbook, no search tool. One agent asked to critique itself often defends its own draft.
Official documentation URL, checked when this seed was written. The prompt and steps are an original AI Playbook Gems playbook, not a quotation of a customer story, and have not been re-run.
Machine-readable copy: JSON
CrewAI handles this as a draft: Hardware, date, and what the authors say they did not test. Do not treat it as a purchase recommendation.
Unverified · docs.crewai.com · 13 Oct 2026
CrewAI handles this as a draft: Term and the sentence in the packet. Do not add outside definitions.
Unverified · docs.crewai.com · 11 Oct 2026
CrewAI handles this as a draft: Each doc's definition, quoted. Do not pick one as official.
Unverified · docs.crewai.com · 30 Sep 2026