User repository on GitHub
Jev-powered release risk scoring and root-cause diagnosis on QA sprint data.
- Forks
- 2
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Jev Qa Analyzer
Two Jev demos over SprintPulse QA data: one scores release risk with a 10-level rubric evaluated against a reference score, the other diagnoses the main risk cause with a 9-label choice question, both sending the same per-ticket signals to Jev's System One API.
- Stars
- 3
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- avi350751
- Last verified
- Oct 2026
Used inJev for Software & DevTools
Highlights
- Two demos of Jev on SprintPulse QA data, answering how risky a release item is and what is driving the risk.
- Release risk scoring uses Jev's score primitive with a 10-level rubric in release_risk_scorer.py and is checked against the dataset's risk_score_10.
- Risk cause diagnosis uses a 9-label choice question in what_causing_the_risk.py and is exploratory because there is no ground truth.
- Input is 70 synthetic tickets; the scripts exclude qa_owner, risk_score_10 and release_readiness from the state sent to Jev.
- Outputs include sprint_results.csv and two sprintpulse_risk_cause CSVs; GitHub metadata lists no license.
Watch out
README and GitHub metadata reviewed 2026-10-17; the excerpt truncates mid-sentence in the reference-column explanation, so accuracy figures, row-level results and setup steps are not evidenced. The dataset is synthetic and the repo was created and pushed 2026-10-02.
Questions about this entry
Short answers drawn from the linked project or page.
A pair of Jev demos on SprintPulse QA data: one scores how risky each release item is with a 10-level rubric, the other diagnoses what is mainly driving that risk with a 9-label choice question.
How risky is this release item, answered with Jev's score primitive over a 10-level rubric, and what is the main thing driving the risk, answered with a choice question over 9 labeled causes.
The README says the release risk output is evaluated against a reference risk_score_10 column in the dataset. The risk cause demo has no ground truth, so the README labels it exploratory rather than scored.
A CSV of 70 synthetic tickets with fields including sprint, module, severity, priority, test coverage, escaped defects, reopen counts, blocked days and story points. The scripts exclude qa_owner, risk_score_10 and release_readiness from the state sent to Jev.
Both scripts send the same per-ticket QA signals to Jev's System One API and differ in the question type, per the README: release_risk_scorer.py and what_causing_the_risk.py are the two entry points.
avi350751 publishes it with no license listed in the metadata; the repository was created and last pushed 2026-10-02, with 3 stars and two forks in the digest.
The excerpt is cut mid-sentence in the reference-column explanation, so accuracy numbers, per-row results, runtime and setup steps are not evidenced, and the synthetic dataset limits what any result would mean.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Show HN: Ad Spend Guard gates budget before the auction, not the creative after.
Show HN: Gating ad budget with a decision modelRead the thread on Hacker NewsX: Field Advisory sends marginal readings to an agronomist instead of a spray.
This post couldn't be loaded here — read it on X.https://x.com/agriwisehq/status/2781000000000000003X: End-to-end tests run by agents
More Jev resources like this
An independent open-source pipeline that gives Jev vision: it detects and tracks objects in images, video, and RGB-D camera feeds, then asks Jev a typed question about each relevant object and prints the chosen answer with its confidence.
Jev Tools & CLIs#community#github#python
Community
CharlesFeng0314/JEV_seesPython
CharlesFeng0314/JEV_seesPythonA Python library that turns Jev-style decision models into ordinary function calls: check returns a bool, classify picks one option, label picks every option that applies, and score rates on a scale, with probabilities behind every answer.
Jev Repos & SDKs#community#github#python
Community
jlowin/vibecheckPython
jlowin/vibecheckPythonAn open-source browser 3D character split between two models: GPT-Live-1 talks with you over WebRTC while Jev reads the live transcript and picks Annie's face, gestures and body language in about 120 ms, with code gates on every answer.
Jev Demos & Experiments#community#github#python
Community
rehan-remade/open-anniePython
rehan-remade/open-anniePythonA Chinese-language e-commerce customer-service demo on FastAPI, LangGraph and React: adaptive retrieval routing with hybrid BM25-plus-vector search, and intent classification switchable between TypeSafe Jev's structured choice interface and DeepSeek.
Jev Demos & Experiments#community#github#python
Community
gbh1234/Adaptive-ragPython
gbh1234/Adaptive-ragPythonEleven small runnable projects for learning Jev and other System One decision models, each lesson pairing a one-command web demo with a whiteboard and README, from the three question types through jobs sorting and contract review to Jev inside a SQL query. Every demo makes live API calls.
Jev Demos & Experiments#community#github#python
Community
aianytime/jev-crash-coursePython
aianytime/jev-crash-coursePythonA browser playground for S1-CED, a small decision model you give a piece of text plus typed questions — yes/no, which-of, or a 0-3 score — and it answers with a probability per option and whether it is confident enough to act or a human should check. Runs on CPU; no GPU or account needed.
Jev Demos & Experiments#community#github#python
Community
ai-yatra/s1ced-playgroundPython
ai-yatra/s1ced-playgroundPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.