TypeSafe AI's Jev Brings Typed Decisions to Agent Loops
Last week, TypeSafe AI released Jev, its first System One model. Founder Diogo Almeida previously worked at OpenAI on the instruction-following research behind ChatGPT.
Jev does not chat, write code, or summarize. It takes unstructured state and returns typed decisions with calibrated probabilities. That makes it a natural fit for the thousands of small judgments inside an agent loop: which model to call, whether a command is safe, which passage is relevant, and whether the agent is actually done.
How Jev Works
Every call sends a state (text or JSON) plus a dictionary of typed questions. TypeSafe's documentation defines three primitives:
- Choice picks one option from a list and returns a probability per option plus confidence.
- Score rates the state on ordered rubric levels and returns probabilities plus confidence.
- Noul returns the probability (0 to 1) that a statement is true.
All questions are evaluated in parallel against the same state in one request. TypeSafe trains Jev with Reinforcement Learning for Calibrated Decisions (RLCD), so higher confidence should track higher accuracy. Choice supports up to 255 options.
The main claims, 193.6x faster and 444.6x cheaper, come from TypeSafe's own workflow evals. The launch post notes that these figures sit on the higher end of real-world gains and use GPT-6 Astra and Fable 5.1 as the reference answer.
Interactive Explainer
An interactive explainer lets readers race a token-by-token LLM against Jev's single pass, move a confidence threshold to see how code gates each decision, estimate monthly cost, and browse all 20 use cases.
20 Agentic Use Cases for Jev
Routing and Orchestration
- Model routing: Score request difficulty, then send it to a fast or strong model based on the result.
via MarkTechPost