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

# Thresholds and calibration

> Turn probabilities into actions. Act on confident answers, hand off the rest.

The API returns calibrated probabilities, so a confidence of 0.9 is right about nine times in ten on data like ours. There’s nothing to configure.

## The act-or-defer pattern

```python theme={null}
route = result.answers["route"]

if route.confidence >= 0.90:
    send_to_team(route.top)   # confident: act now
else:
    ask_a_human(ticket)       # unsure: hand it off
```

## Choosing a threshold

<Steps>
  <Step>Collect a few hundred real examples with known answers.</Step>
  <Step>Send them through the API and record each confidence and whether the top answer was right.</Step>
  <Step>For each candidate threshold, count how many you’d automate and how accurate those would be.</Step>
  <Step>Pick the lowest threshold that meets your accuracy target.</Step>
</Steps>

<Tip>
  Recheck your threshold when your inputs change a lot, for example a new product line or a new language.
</Tip>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.