Automated README summary
Automatically summarized from the README on 22 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
DiffJury is a Next.js web app for developers: paste a public GitHub pull request URL and it fetches the PR dossier and returns a TypeSafe Jev judgment with risk bars, noul probabilities, and a verdict.
How it uses Jev
A single server-only TypeSafeClient.systemOne call with model jev-latest judges the PR dossier (title, body, diff, contributors). Jev answers typed questions: risk, review_depth, needs_design, needs_security, merge_blocker, missing_tests, docs_debt, blast_radius, verdict. Results render as risk bars, noul probabilities, and a verdict in the split view.
Primitives:choicescorenoul
Technique worth stealing
Trim large PRs locally to fit Jev's ~32k/64k token limits while keeping small PRs unchanged.
Try it
npm install, set TYPESAFE_API_KEY in .env.local, npm run dev, open http://localhost:3000.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.95
- Shows a System One patternnot found in the excerpt0.18
- Describes handling uncertaintynot found in the excerpt0.09
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.76
- Top-10 learning shortlist signalnot found in the excerpt0.33
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.94 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 22 Sept 2026.