> For the complete documentation index, see [llms.txt](https://guides.tability.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guides.tability.io/docs/become-a-tability-power-user/features/ai-features/ai-metric-detection.md).

# AI metric detection

<figure><img src="/files/o7c5B0aAnmSnWmOznINB" alt=""><figcaption></figcaption></figure>

Tability's **Plan Editor** leverages AI to automatically detect the type of goal as well as the starting value and target that you're going for.

It uses our OpenAI integration to analyse the text describing your goal and update the outcome/key result accordingly.

## How to use the AI metric detection

The AI metric detection is turned on by default when you create a workspace. To use it, you simple need to add new outcomes to your plan using the **Plan Editor**.

{% hint style="info" %}
For more info on usage and how OpenAI handles your data, visit our [OpenAI](/docs/become-a-tability-power-user/integrations/openai.md) integration page.
{% endhint %}

## How to disable the AI metric detection

Visit the privacy settings of your workspace to disable the AI metrics detection. See the [OpenAI](/docs/become-a-tability-power-user/integrations/openai.md) page for more info.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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://guides.tability.io/docs/become-a-tability-power-user/features/ai-features/ai-metric-detection.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.