pydantic-jev-examples

Pydantic AI capabilities made stronger with Jev: small runnable demos, one file each

How it uses Jev

These are small, runnable examples of Pydantic AI agents where Jev makes the quick calls: is this prompt ok, should this command run, should the bird flap.

Use cases

  • Yes or no. "Is this prompt harmful?" You get back a probability from 0 to 1.
  • Pick one. "Run it, reject it, or ask a human?" You get back the pick and how sure Jev is.
  • one small file with the Jev part, named after what it does
  • demo.py , which plugs it in and shows it working
  • a README with the snippet, the run command, and how it works

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to pydantic-jev-examples

Browse all
typesafe-jev-workflow project preview
Async LangGraph workflow that gets a typed Jev Choice (invoice or general) and routes each inbound email to the matching handler.
typesafe-ai-jev-example project preview
Demos & playgrounds
Hands-on demos for TypeSafe's Jev (System One) model: six runnable examples and four field notes. Runs offline with no API key; samples/ holds real measured output from jev-1.13.0.
A home that understands project preview
Turn the state of your home into typed decisions, sensors, and smarter automations.
Jev as an LLM prompt guardrail inside the agentgateway proxy, with tracing and cost tracking.
jev-exploration project preview
Benchmarks & research
Jev (TypeSafe) exploratory thread: claim audit, live demos, and runnable code
jev-demo project preview
Demos & playgrounds
TypeSafe Jev(System One 决策模型)零依赖网页体验台:浏览器操作 / 意图识别 / Agent 上下文裁剪三大预设场景,发送状态与类型化问题,拿到带校准概率的结构化答案
jev-cookbook (paramjeetn) project preview
The complete cookbook for Jev by TypeSafe AI — 120+ use cases, 10 runnable examples, 4 composition patterns, and first-principles theory for the world's first System One AI model.
jevlike project preview
Benchmarks & research
Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos.
jevbetter project preview
Benchmarks & research
A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.