Finish substantial tasks with evidence, not guesses.
What it does
Guides substantial tasks through independent review and repeated verification so the final deliverable is supported by evidence.
When to use it
Use when the user requests delegated work, independent reviewers, repeated improvement, benchmark comparisons, prompt enhancement, or explicit quality gates.
How to use it
It changes how the agent completes substantial tasks by adding acceptance gates, independent verification, revision loops, and an evidence-backed final response.
Good to know
- starts helper agents, number unstated
Latest review
What you need · 0
No setup requirements listed.
Access · 0
No additional actions listed.