Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Flow Steward extension that evaluates structured decisions through project connections using TypeSafe AI's JEV model, plus an importable support-request classification workflow for operators.
How it uses Jev
The 'Evaluate with JEV' connector sends a state (text, object, or array) and named choice/score/noul questions to the fixed SystemOne endpoint. The triage example asks category (choice), urgency (score), and human-required (noul), then routes to manual_review or a routing_key based on confidence thresholds.
Primitives:choicescorenoul
Technique worth stealing
Combine choice, score, and noul questions in one call, then gate routing on calibrated confidence thresholds.
Try it
Install the release ZIP, configure a project connection with a TypeSafe key, import the example YAML, and run jev_support_triage with a message.
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 material0.74
- Shows a System One patternnot found in the excerpt0.09
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.31
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.09 / 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 3 Nov 2026.