Use Cases / pr-risk
Jev PR Risk Judge
Busy repos need a fast risk signal on PR title + diff summary before deep human review. Chat LLMs are slow and hard to threshold; regex rules miss auth and secret leaks.
Try a related template free on this host — 5 anonymous real-API runs with no signup — then ship the same schema with a prepaid jv_live_ key. See is Jev free? and playground.
Why Jev
Pass PR title, summary, and touched paths as state. Get a Choice verdict (allow / review / block), a risk Score, and a needs_security_review Noul your bot can enforce. Example: removing JWT on /admin → block + high risk.
How to define the decision
State should include title, short diff summary, and touched paths. Ask Choice for verdict, Score for risk, Noul for needs_security_review. Align verdict labels with what your bot understands.
When to use Jev
- CI or bot first-pass on PR summaries
- Security review queue prioritization
- High-blast-radius path detection (auth, billing, admin)
When not to use Jev
- Replacing human security review on sensitive changes
- Full static analysis or SAST of the diff
- Generating the code fix
Sample input and output
From the live tool template. Run it in the playground for a real API response — sample labels below are illustrative until you click Run.
Input
title: Relax auth on /admin for staging tests summary: Removes JWT check on /admin/*; adds console.log of session cookies. files: app/api/admin/route.ts, middleware.ts
Sample display fields
- verdict: block · 88%
- risk: 0.86 · high
- needs_security_review: yes · 92%
Block or high risk → require security review or hold merge. Low-confidence allow → treat as review. Model scores never override hard CODEOWNERS or branch protection.
Failure modes and human fallback
- Upstream or network errors: retry with backoff; do not invent a decision.
- Low confidence: route to a human queue or safer default — never auto-act on money/destructive tools.
- Schema drift: keep a golden fixture set in CI so label changes fail the build before production.
- Jev reads summaries you provide — not a substitute for diff scanners.
- Fail closed (block or human review) on API failure.
- Keep IAM and branch protection as hard controls.
API example
Same prepaid jv_live_ balance as tools. Output tokens are free on this host's metering model.
curl https://jevtypesafe.org/api/v1/decide \
-H "Authorization: Bearer jv_live_YOUR_KEY_HERE" \
-H "Content-Type: application/json" \
-d '{"state":"PR risk judge\nTitle: Relax auth on /admin for staging tests\nFiles: app/api/admin/route.ts, middleware.ts\nSummary:\nRemoves JWT check on /admin/*; adds console.log of session cookies.","questions":{"verdict":{"type":"choice","instructions":"Merge recommendation for a careful production team?","criteria":{"approve":"low risk, fine to merge with normal review","caution":"merge only with extra eyes / staging proof","block":"do not merge until security/auth issues are fixed"}},"risk":{"type":"score","instructions":"Overall production risk from 0 (safe) to 1 (severe).","criteria":["cosmetic","limited","material","severe"]},"needs_security_review":{"type":"noul","instructions":"Should security review this before merge?"}}}'FAQ
- Which tool should I open first?
- Open PR Risk Judge under Tools, run the sample, then wire the same questions into your CI via /api/v1/decide.
- Can this approve merges automatically?
- Only if your risk appetite allows — and never alone for auth/billing paths. Prefer “block or escalate” over silent allow on low confidence.
Related use cases
Ready to build?
Free anonymous tool runs, then prepaid packs and a jv_live_ key — independent host, not affiliated with TypeSafe AI.