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

# Confidence threshold

> Send a field to review when the model is not sure enough.

The **Confidence threshold** validator sets the minimum confidence the model must have in a field for it to be auto-approved. Anything below the threshold is flagged, so a human looks at the values the model was unsure about and the rest pass through untouched.

This is the main dial between automation rate and accuracy. A high threshold catches more mistakes but sends more documents to review; a low one automates more and lets more mistakes through.

## Options

| Option | What it does |
| - | - |
| **Threshold** | The minimum confidence, as a percentage. Pick one of the presets or set a custom value with the slider. |

<Tip>
  Rather than guessing, run a batch of documents through and look at how often the model is right at each confidence level. Start strict, then lower the threshold on fields that prove reliable.
</Tip>

## How it behaves

| Situation | Result |
| - | - |
| Confidence at or above the threshold | Passes |
| Confidence below the threshold | Flagged for review |
| The field is empty | Passes — use [Cannot be empty](/core-concepts/ai-model/validators) to require a value |
| The reviewer already edited the field | Skipped, since the value is now human-entered |

<Note>
  This validator always reports a **warning**, so the reviewer can accept a low-confidence value as it stands. The warning/error setting shown in the panel has no effect here — if a field must be corrected before the review can be completed, enforce it with a validator that supports errors, such as [RegExp](/core-concepts/ai-model/regex-validator) or Cannot be empty.
</Note>

Setting every confidence threshold to `0` makes every run stop for human review, which is occasionally useful when you want a person to see everything.