> ## Documentation Index
> Fetch the complete documentation index at: https://docs.levanto.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Yes/No decisions

> Binary decisions with probability, answer, and confidence.

Use Yes/No for binary questions. Sage returns `probability` (P(yes)), `answer` (`"yes"`/`"no"`), and `confidence` (decisiveness from tie).

## Request

```json theme={null}
{
  "content": "Marketing email draft promotes \"guaranteed 40% returns\" and describes the product as \"risk-free\" for accredited investors.",
  "question": {
    "id": "needs_compliance_review",
    "kind": "yesno",
    "instructions": "Does this copy require compliance review before send?"
  }
}
```

## Response

```json theme={null}
{
  "id": "needs_compliance_review",
  "kind": "yesno",
  "result": {
    "probability": 0.92,
    "confidence": 0.84,
    "answer": "yes"
  },
  "meta": { "model": "levanto-sage-v0.5", "latency_ms": 97.4 }
}
```

## Fields

| Field         | Description                                                                                          |
| ------------- | ---------------------------------------------------------------------------------------------------- |
| `probability` | P(yes), in `[0, 1]`                                                                                  |
| `answer`      | `"yes"` if `probability ≥ 0.5`, else `"no"`                                                          |
| `confidence`  | Decisiveness from a tie: `2 × abs(probability − 0.5)` — `0` at a coin-flip (`0.5`), `1` at certainty |

## Threshold guidance

Sage always returns a decision signal. Your application decides what to do next:

* **High confidence** — automate
* **Medium confidence** — review
* **Low confidence** — escalate to a human or ask for more context

Sage supports low-confidence routing; it does not abstain.