CalibratedDecisions.

Repo · Guides & docs

TypeSafe AI — api-evangelist

Independent public-surface profile of TypeSafe AI: System One endpoint shape, OpenAPI, agent card, MCP, skills, SDKs, limits, and security notes,…

Open github.com ↗

From the repository

TypeSafe AI is a San Francisco AI lab building System One models — a class of model trained to return typed, calibrated decisions for software instead of generated text. Its flagship and first System One model, Jev, is served by a single HTTP endpoint: POST /v1/systemone takes a `state` (a string, JSON object, or array) plus a map of typed…

agent-nativeagent-skillsapis-jsonartificial-intelligenceclassificationcontent-moderationdecision-supportdeveloper-toolsinferencellm-alternativemachine-learningmcpstructured-outputs

How builders describe it

Independent public-surface profile of TypeSafe AI: System One endpoint shape, OpenAPI, agent card, MCP, skills, SDKs, limits, and security notes, with no software to download.

The decision Jev makes

Where to start: the quickstart, the decision primitives and the patterns.

Where it fits

The official starting points plus the best explainers, videos and articles about Jev and RLCD. All 342 guides & docs projects →

Related projects