> For the complete documentation index, see [llms.txt](https://docs.screendesk.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.screendesk.io/debug-with-ai/ai-settings.md).

# AI settings

Control workspace AI processing, automatic report analysis, AI labels, and your Gemini API key.

Open **Settings → AI & Intelligence** to control how Screendesk processes new workspace content.

## Enable AI processing

**AI processing** is the workspace-wide control for sending new content to AI and speech-processing providers.

When it is off:

* New AI and speech processing is paused.
* Existing transcripts and AI-generated content remain available.
* Your saved automation settings and Gemini key are preserved.

Turning processing back on allows new work. It does not automatically regenerate all historical reports or backfill everything created while processing was off.

## Turn on report intelligence

Under **Automations**, enable **Report intelligence** to automatically analyze eligible new recordings, capture videos, and screenshots.

The analysis can produce summaries, issue findings, and reproduction steps. The output depends on the report type and the evidence captured. See [Report intelligence](/debug-with-ai/ai-summary.md).

The control is paused when workspace AI processing is off. If an upgrade prompt appears, the feature is not available on the workspace's current plan.

## Choose how AI labels are applied

**AI labels** matches reports to existing workspace labels using report intelligence.

| Application mode   | Behavior                                                          |
| ------------------ | ----------------------------------------------------------------- |
| **Off**            | Does not suggest or apply labels                                  |
| **Suggest only**   | Shows matching labels in report Details                           |
| **Require review** | Sends matches to the review queue before applying them            |
| **Automatic**      | Adds matching labels automatically; existing labels are preserved |

For **Require review**, choose who can approve: owners and admins, or owners, admins, and editors.

Use clear, distinct workspace labels so a suggested match is useful to the team.

## Bring your own Gemini key

Screendesk can use its managed Gemini key, or you can supply your own key for generative AI.

1. In **Bring your own key**, click **Add key**.
2. Enter your Gemini API key.
3. Click **Validate and add**.

Screendesk validates the key before saving it. A saved key is encrypted at rest and is not displayed again. The status changes from **Using Screendesk key** to **Using your key**.

Usage made with your key is billed to your provider account. This setting does not change your Screendesk feature entitlement.

### Replace or remove a key

Click **Manage key** to enter a replacement and choose **Validate and replace**.

Choose **Remove** to return to the Screendesk-managed key.

### If the key needs attention

A **Needs attention** status means Gemini could not use the configured key, for example because authentication or permissions failed. Replace it with a valid key, or remove it to return to the managed key. Screendesk does not silently switch to its managed key when your configured key is invalid.

When AI processing is off, the key is inactive, but you can still manage it.

## Configure knowledge and resolution separately

Enabling report intelligence does not connect a knowledge base or enable ticket investigations.

* Add product knowledge in [Data Sources](/debug-with-ai/data-sources.md).
* Configure the Zendesk workflow in [AI Resolution](/debug-with-ai/ai-resolution.md).


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.screendesk.io/debug-with-ai/ai-settings.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.