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

# AI impact dashboard for GitHub Copilot

We're excited to invite all cloud customers to try our Copilot Dashboard in [Engineering Intelligence](/improve/eng-intelligence.md). Using this dashboard, you’ll be able to measure adoption and impact of AI coding tools, starting with GitHub Copilot, across your engineering teams.

<figure><img src="/files/rQukb8ZmBYxiOAGKSXQ1" alt="" width="563"><figcaption></figcaption></figure>

### What's new

#### Impact by team AI adoption rate

View each team’s Copilot adoption rate, and correlate team adoption rate to delivery and reliability metrics. Adoption rates are provided daily by comparing active users against Copilot seats. Choose between different performance metrics by using the dropdown on the top right area of this chart.

#### Impact between Copilot users vs Non-Copilot users

Compare delivery and reliability side-by-side between users who leveraged AI tools within the last 7 days, and those who did not. Understand whether recent AI usage affects engineering performance. Choose between different performance metrics by using the dropdown on the top right area of this chart.

Cortex will automatically create an AI Usage user label for your team members, and keep that updated based on whether each member was active in Copilot within the last 7 days or not.

#### AI adoption insights

Track how many developers are actively usually Copilot and see how adoption has trended over time.

#### Dive deeper in Metrics Explorer

See two new metrics, AI Adoption Rate and Active AI Users, within a new AI Tools category in Metrics Explorer. Group any Eng Intel Metric by the Cortex-generated AI Usage user label to compare performance between AI Users (Last 7 days) and Non-AI Users (Last 7 days).

### Getting started

#### Add data from Copilot

{% hint style="info" %}
Note that Copilot usage history cannot be backfilled. Your dashboard will populate over time as usage data is collected.
{% endhint %}

Data integration for Copilot metrics is the first step. If you have already configured the [GitHub integration](/ingesting-data-into-cortex/integrations/github.md), you must update your permissions to enable the ability to pull in Copilot data.

See the instructions below for your integration method:

* Cortex GitHub app
  * [Re-authorize your Cortex GitHub app](https://support.getcortexapp.com/hc/en-us/articles/41736643663387-Why-is-Cortex-requesting-that-I-re-authorize-the-GitHub-app-for-Copilot-metric-permissions) to accept two new permissions.
* Custom GitHub App
  * Add the following permission to your custom GitHub App: Read-only access to Administration.
* Personal Access Token
  * Add the following permission to your PAT: Read-only access to Administration.

#### View the Copilot Dashboard

Once your integration is configured with the necessary permissions, navigate to **Eng Intelligence > Dashboards > Copilot Dashboard**.

Note that Copilot usage history cannot be backfilled. Your dashboard will populate over time as usage data is collected.

See the full documentation: [Copilot Dashboard](/improve/eng-intelligence/dashboards/ai-impact.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 dynamically by asking a question.

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

```
GET https://docs.cortex.io/resources/beta/ai-dashboard.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.