Automated README summary
Automatically summarized from the README on 30 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A learning project: a Go service that accepts support tickets over HTTP, classifies them in the background, and routes them to a team or a human, streaming status to the submitter via SSE.
How it uses Jev
The worker asks Jev three questions in one call on the ticket text: whether it is a complaint, which team (billing, technical, account, feature_request, other), and priority (low, normal, high, critical). Confidence thresholds decide classified vs needs_human.
Primitives:choicescore
Technique worth stealing
At-least-once Kafka delivery with an idempotent consumer: conditional UPDATE on pending status plus transactional outbox, so duplicates never duplicate state.
Try it
make up, run cmd/migrate up with DATABASE_URL, then go run ./cmd/api and go run ./cmd/worker.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 patternFound in material0.91
- Describes handling uncertaintyFound in material0.92
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.85
- Top-10 learning shortlist signalnot found in the excerpt0.32
- Is a replica of the modelunclear0.40
- Solves a common problem (0–2)score on a 0–2 scale1.59 / 2
- About JevFound in material0.99
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 30 Oct 2026.