Automated README summary
Automatically summarized from the README on 29 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Databricks App that turns one prompt into a purpose-built agent on the fly. It discovers models, MCP servers, and skills from Unity Catalog metadata, uses JEV to compose an agent spec, then builds and runs the agent with the OpenAI Agents SDK.
How it uses Jev
JEV makes three decisions in one parallel call: a choice over Foundation Model API endpoints to pick the model, and a noul per candidate MCP server and per candidate skill to score relevance. Items above a threshold are selected. The resulting spec drives agent composition and invocation.
Primitives:choicenoul
Technique worth stealing
Use one JEV round trip to make typed, calibrated selections from enterprise metadata, avoiding brittle single-pick or LLM discovery loops.
Try it
Deploy as a Databricks App or run locally with uvicorn app:app --reload --port 8080 after setting JEV_API_KEY and Databricks credentials.
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 material0.96
- Shows a System One patternFound in material0.76
- Describes handling uncertaintynot found in the excerpt0.20
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.91
- Top-10 learning shortlist signalunclear0.52
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.07 / 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 29 Sept 2026.