# System One model

> System One batches typed questions in one forward pass, with probabilities you can threshold. Routing and composite scoring. Not a chat LLM.

## Answer

System One is TypeSafe's model family for parallel typed evaluation: many questions, one forward pass, calibrated probabilities.

## Not a chat model

System One models do not freely generate prose. They answer constrained questions (which option, what score, or how true) with calibrated probabilities suitable for routing and gates.

## Latency and cost profile

TypeSafe publishes end-to-end latencies on the order of tens to hundreds of milliseconds for typical parallel question batches, with pricing oriented toward high-volume decision workloads rather than long completions.

## Patterns

Official docs describe speculative fan-out, confidence-gated routing, composite scoring, and hierarchical classification. All of that maps cleanly to Choice, Score, and Noul primitives.

## Batching questions

System One shines when you ask many small questions about the same snapshot of state. One forward pass amortizes context loading and keeps latencies predictable compared with serial chat calls that repeat the same preamble.

## Calibration matters

Probabilities are meant to be thresholded. If your pipeline needs a 0.95 bar for auto-approval, you can tune policies in code and measure drift over time. That is harder when a classifier returns unstructured text.

## Operational footprint

Because outputs are discrete, logging and replay are straightforward: store the state hash, questions, and probability vector. Incident review does not require reading pages of generated prose.

## FAQ

### Does System One chat?

System One models do not freely generate prose. They answer constrained questions, such as which option, what score, or how true, with calibrated probabilities.

### Why ask so many questions at once?

System One shines when you ask many small questions about the same snapshot of state. One forward pass keeps latencies predictable compared with serial chat calls that repeat the same preamble.

### What do I do with the probabilities?

Probabilities are meant to be thresholded. If your pipeline needs a 0.95 bar for auto-approval, you can tune policies in code and measure drift over time.

Directory copy checked 2026-09-30. This directory is independent of TypeSafe AI unless a listing says it is official.
Canonical: https://jev.aitools.fyi/learn/system-one
Markdown: https://jev.aitools.fyi/learn/system-one.md