muse-jev-playbook
Jev decision layer for Muse: a fast, cheap TypeSafe AI gate before expensive agent work — confidence policy, recipes, reference router, honest measurement.
How it uses Jev
Use TypeSafe AI's Jev as a cheap, fast decision layer inside an AI agent workflow — triage, classify, score, and gate work before expensive steps (browser, deep research, retries, subagents).
Use cases
- choice "What kind of work does this need?" → research (confidence 0.93)
- noul "Should we cap this research at 5 sources instead of going deep?" → yes (0.88)
- score "How much effort is justified?" → Heavy (0.71)
- Language
- Python 100%
- License
- MIT
- Last activity
- Sep 2026
- Added
- 2026-09-23
- Stars at snapshot
- 16
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.