Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Decision Kernel exposes TypeSafe Jev as a fast, calibrated, low-cost judgment API for small SaaS, support teams, and agent developers. It classifies text into triage, urgency, spam, tone, and risk, and provides an agent-safety gate for actions.
How it uses Jev
Jev makes decisions on text for /classify (triage, urgency, spam, tone, risk) and on action, cost, goal, and lastActions for /guard (spend, off_goal, duplicate, undoable, last_ok, lead_real). Results are returned as calibrated probabilities and used in code to route or gate actions.
Primitives:choicescorenoul
Technique worth stealing
Use a decision model for typed, calibrated answers instead of LLM prose when possible answers are known.
Try it
curl -X POST https://decision-kernel.pickaxe.workers.dev/classify -H "Content-Type: application/json" -d '{"text":"my app keeps crashing when I try to export my data, please help"}'
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 material0.91
- Shows a System One patternFound in material0.76
- Describes handling uncertaintynot found in the excerpt0.12
- Reports measured numbersunclear0.48
- Is a runnable toolFound in material0.84
- Top-10 learning shortlist signalunclear0.41
- Is a replica of the modelnot found in the excerpt0.13
- Solves a common problem (0–2)score on a 0–2 scale1.99 / 2
- About JevFound in material0.97
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 Sept 2026.