> For the complete documentation index, see [llms.txt](https://help.swarmia.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.swarmia.com/features/ai-impact.md).

# AI impact

Track AI coding tool adoption, autonomy, impact, and cost in Swarmia.

Swarmia's AI impact pages help you connect AI coding tools, track adoption and agent autonomy, and understand what AI-assisted work costs and delivers.

## Get started

* [Set up AI coding tool integrations](https://help.swarmia.com/settings/integrations/ai-coding-tool-integrations.md) for GitHub Copilot, Cursor, Claude Code, and Codex.
* [Understand the impact of AI tools](https://help.swarmia.com/guides/understand-the-impact-of-ai-tools.md) with a practical guide for measuring adoption, productivity, agent usage, and developer sentiment.

## Feature pages

* [Overview](https://help.swarmia.com/features/ai-impact/overview.md): Scan AI adoption, throughput, review load, quality, and cost in one place.
* [AI adoption](https://help.swarmia.com/features/ai-impact/ai-adoption.md): See which AI coding tools your teams have and how much of their work those tools touch.
  * [Users and licenses](https://help.swarmia.com/features/ai-impact/ai-adoption/users-and-licenses.md): Track licenses, active users, and idle seats across teams.
  * [AI-assisted PRs](https://help.swarmia.com/features/ai-impact/ai-adoption/ai-assisted-prs.md): Track merged pull requests by AI tool and mode, and explore the pull requests behind the numbers.
* [AI readiness](https://help.swarmia.com/features/ai-impact/ai-readiness.md): See which repositories have configuration files for your AI tools.
* [AI autonomy](https://help.swarmia.com/features/ai-impact/ai-autonomy.md): See how much of your pull request work agents author and review on their own.
  * [Cloud agents](https://help.swarmia.com/features/ai-impact/ai-autonomy/cloud-agents.md): Analyze pull requests created by AI agents running in the cloud.
  * [Review agents](https://help.swarmia.com/features/ai-impact/ai-autonomy/review-agents.md): See which AI agents review your pull requests and how much code they cover.
* [AI ROI](https://help.swarmia.com/features/ai-impact/ai-roi.md): Weigh what your AI tools and engineering time cost against what your teams deliver.
  * [Throughput & cost](https://help.swarmia.com/features/ai-impact/ai-roi/throughput-and-cost.md): Compare cost per story, pull request, and line changed against throughput per FTE.
  * [AI cost](https://help.swarmia.com/features/ai-impact/ai-roi/ai-cost.md): Track AI token usage from your AI coding tools, and see how it breaks down by team, person, and work.
* [AI tool detection & filters](https://help.swarmia.com/features/ai-impact/ai-tool-detection-and-filters.md): Learn how Swarmia detects AI tool usage and how to filter AI-assisted work.


---

# 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://help.swarmia.com/features/ai-impact.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.
