Show HN: Knowledge Signal – A JEV-powered rubric assessment tool for study notes
Show HN thread for Knowledge Signal, an open-source prototype that grades study notes against a rubric with Jev.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This is a Hacker News Show HN thread titled 'Knowledge Signal - A JEV-powered rubric assessment tool for study notes'. The list snippet says the author built an open-source prototype that turns study notes into an assessment, apparently by scoring them against a rubric with Jev.
No thread or repository content was fetched, so the rubric levels, interface and evaluation are not available here. It fits the common use of Score questions for grading text against ordered criteria.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Score | How well do these study notes meet each rubric criterion?(inferred) | — |
How it works
- Paste or upload study notes
- Jev scores the notes against rubric criteria
- Show the assessment to the learner
Strengths
- Fast rubric feedback, per the title
Caveats
- Only the title and a snippet are available
- Prototype
At a glance
- Type
- Discussion
- Status
- discussion
- Has code
- yes
Use cases and integrations
How curated lists describe it
I built Knowledge Signal, an open-source prototype that turns study notes into…
wh000wh000/awesome-jev-live
Frequently asked questions
What is Knowledge Signal?
An open-source prototype that assesses study notes against a rubric with Jev, per the thread.
Where is it discussed?
news.ycombinator.com/item?id=49840561.
Is the code available?
The thread describes it as open source; the repository is not identified here.
Related projects
TypeSafe cookbook on why repeated Jev calls can differ, showing how an abstention rule raises repeat agreement.
ArticleproductionClaude Code and Codex skills plus a study course for building with Jev, including Jevaluate, which rates how well projects use Jev.
ProjectbetaRead-aloud English tutor: streaming ASR transcribes, then Jev judges word by word whether each word was read correctly.
ProjectprototypeJavaScriptConcept prototype for marking NZQA scripts from rubric criteria alone with one Jev call per script and confidence-based triage.
ProjectprototypeJavaScriptLearning lab for DeepEval with Jev as the judge: replayed evaluations, adjustable decision rules, release gates and drift alerts.
ProjectprototypePythonAwesome list and guide to System One models (Jev, Laya and others) organized around a five-stage agent lifecycle, with comparison tables.
Projectproduction