Automated README summary
Automatically summarized from the README on 25 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python tool that tags thousands of search queries by intent and product using Jev, TypeSafe AI's System One model. It gates low-confidence results for human review and joins labels to clicks and bookings.
How it uses Jev
Jev answers three questions per query: intent (choice among 7 buckets), product (choice among 9 buckets), and new_buyer (noul probability). The same question card is sent with each query; only the state line changes. Results are used in code to tag queries, with confidence gating at 0.70.
Primitives:choicenoul
Technique worth stealing
Send the same question card with every query, changing only the state line, so extra questions cost almost nothing.
Try it
Run `python jev_tag.py examples/queries.sample.csv --dry-run` to see the request, then tag with an OpenRouter key.
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 material0.92
- Shows a System One patternFound in material0.81
- Describes handling uncertaintyFound in material0.94
- Reports measured numbersFound in material0.96
- Is a runnable toolnot found in the excerpt0.26
- Top-10 learning shortlist signalFound in material0.61
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.12 / 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 25 Sept 2026.