Automated README summary
Automatically summarized from the README on 20 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jevex is a Convex component for developers who want to filter and sort table rows by plain-English judgments. You define questions about a table, and jevex asks Jev when rows change, storing answers in an indexed table for fast queries.
How it uses Jev
You define an index with a state function and typed questions (choice, score, noul). When a row changes, jevex hashes the state and questions; if unchanged it skips, if cached it settles in-transaction, otherwise it queues the row. A dispatcher batches queued rows (up to 20 per request) and calls Jev. Answers are stored in an indexed table, and queries like top() read index ranges without calling a model.
Primitives:choicescorenoul
Technique worth stealing
Judge on write: run the model once per row change, store answers in an indexed table, and let reads be fast indexed queries.
Try it
Install @mbilskilets/jevex, set TYPESAFE_API_KEY via npx convex env set, define an index, and hook it to writes with a convex-helpers trigger.
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 material0.89
- Shows a System One patternunclear0.54
- Describes handling uncertaintynot found in the excerpt0.11
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.16 / 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 20 Oct 2026.