# Knowledge Learning

The Knowledge Learning settings are in **Settings > Configuration > Knowledge Learning**. These settings apply to all bots in your tenant. Two of the three configurations on this page are deprecated and have no effect.

### Score Threshold

| **Type**    | Decimal |
| ----------- | ------- |
| **Default** | `0.7`   |

Sets the minimum similarity score a Knowledge Base (KB) article must achieve to be returned as a match during Knowledge Learning. Raising this value reduces the number of matches returned but increases confidence; lowering it returns more matches at the cost of precision. Adjust this value if Knowledge Learning is surfacing too many low-quality KB suggestions, or missing articles that should be linked.

{% hint style="info" %}
Set this value between `0.0` and `1.0`. The system does not enforce a range, but similarity scores themselves fall within that range, so values outside it are not meaningful. 
{% endhint %}

{% hint style="warning" %}
Changing this value does not take effect automatically. A new Knowledge Learning training run is required to rebuild the model with the updated threshold.
{% endhint %}

## Deprecated configurations

### Use KB Subjects

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

This configuration is deprecated and has no effect.

### Use KB Contents

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

This configuration is deprecated and has no effect.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aisera.com/aisera-platform/tenant-setup/aisera-platform-configuration/tenant-configuration-settings/knowledge-learning.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.