Automated README summary
Automatically summarized from the README on 1 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Companion code for the Udemy course "Master TypeSafe Jev AI". It contains three small Python scripts, one per TypeSafe AI primitive, plus a ticket-router milestone project that reads departments from rules.yaml.
How it uses Jev
Jev answers typed questions instead of generating text. choice_ques.py routes a GitHub issue to a team, score_ques.py rates bug severity and frustration, noul_ques.py runs a yes/no PR checklist. The router asks Jev which department should handle a ticket and sends it to a human when confidence is below min_probability.
Primitives:choicescorenoul
Technique worth stealing
Branch on the returned numbers (confidence, probabilities, noul) rather than only the top answer, and tune thresholds on your own data.
Try it
Install typesafe-sdk==0.7.5, python-dotenv and pyyaml, create .env with an API key, then run uv run python choice_ques.py.
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 material0.96
- Shows a System One patternFound in material0.64
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolunclear0.42
- Top-10 learning shortlist signalunclear0.40
- Is a replica of the modelnot found in the excerpt0.24
- Solves a common problem (0–2)score on a 0–2 scale1.18 / 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 1 Nov 2026.