> ## Documentation Index
> Fetch the complete documentation index at: https://secndai.manicule.dev/llms.txt
> Use this file to discover all available pages before exploring further.
> For every page in one file, fetch https://secndai.manicule.dev/llms-full.txt (large).
> To search and read these docs as tools, connect the MCP server at https://secndai.manicule.dev/api/mcp.
> Every agent surface: https://secndai.manicule.dev/.well-known/llms-manifest.json

# True/false (/primitives/true-false)

<!-- agent-signals: reading_time_min: 1 · est_tokens: 244 · updated: 2026-11-12 -->
Related: [Choice](/primitives/choice.md), [Score](/primitives/score.md), [Confidence and the gate](/confidence.md)

> Ask whether one stated proposition holds.

The API type is `noul`. Write one proposition with a clear meaning for both true and false. Do not include `options` or `levels`.

```json title="request"
{
  "model": "ren-zero-2026-11-12",
  "type": "noul",
  "situation": "The customer wrote: Please cancel my subscription before it renews.",
  "question": "Does the customer explicitly request cancellation?",
  "threshold": 0.9
}
```

The response's `probability` is the probability of true. `probabilities` has `"true"` and `"false"` keys. `choice` is the more probable answer, and `confidence` is the probability of that chosen answer.

A low `probability` can therefore accompany high confidence in false. Always read `choice` and `action` before acting; `action: "act"` does not mean the proposition is true.

For missing evidence, ask a separate question or escalate. False should not silently mean both “contradicted” and “unknown” when those require different actions.