Enables AI agents to make fast, low-cost, typed decisions via a TypeSafe System One, providing routing, scoring, approval, and escalation through tools such as ask, choice, score, and noul.
Enables MCP clients to run fast, local, non-autoregressive System-1 decisions on text, including classification, triage, routing, and safety gating, via six typed tools with probabilistic outputs.
Enables coding agents to ask typed yes/no, choice, score, and bounding-box questions about code, diffs, logs, and screenshots, returning structured decisions with calibrated confidence, caching, and cost controls.