> 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/settings/integrations/ai-coding-tool-integrations/custom-ai-tool-integrations/connect-kiro-to-swarmia.md).

# Connect Kiro to Swarmia

Send Kiro Enterprise usage data to Swarmia to track AI adoption and AI-assisted pull requests.

## Requirements

This integration requires **Kiro Enterprise**. Kiro's [per-user activity reports](https://kiro.dev/docs/enterprise/monitor-and-track/user-activity/) are an Enterprise feature. Individual Kiro plans don't provide the organization-level, per-user usage export that Swarmia needs.

You also need:

* Access to the AWS account and Region where your engineers are subscribed to Kiro
* An Amazon S3 bucket for Kiro's usage reports
* The [organization admin](https://help.swarmia.com/settings/organization/managing-users-and-roles.md) role in Swarmia

## Set up Kiro usage reports

In the Kiro console, go to **Settings** and enable **Kiro user activity reports**. Configure an S3 location, then enable **Collect granular metrics per user**.

Kiro writes daily CSV reports to that bucket for each client type, including the IDE, CLI, and plugin. Reports include each user's email address, subscription tier, total messages, and credit usage. The first report is available after Kiro's next daily export cycle at 02:00 UTC.

For S3 bucket requirements, permissions, and report details, see [viewing per-user activity in Kiro](https://kiro.dev/docs/enterprise/monitor-and-track/user-activity/).

## Send Kiro usage data to Swarmia

Create a custom AI tool named **Kiro** with `kiro` as its API identifier in [Settings → AI tools](https://app.swarmia.com/settings/ai-assistants). If your organization has connected Kiro Web to GitHub, select the `kiro-agent` GitHub identity under **Linked authors**. This attributes Kiro Web activity from `kiro-agent[bot]` with high confidence.

Then run a daily job that reads Kiro's CSV reports from S3 and sends the data to Swarmia's [additional AI integrations API](https://help.swarmia.com/settings/integrations/swarmia-apis/additional-ai-integrations.md).

Kiro's `user_report` files include a `User_Email` field. Match it to the Swarmia author email, and combine each user's daily records across Kiro client types before sending them to Swarmia.

Set `is_enabled` for every subscribed user, and `is_active` when they used Kiro that day. Import Kiro subscription data separately to include subscribed users with no activity. For authentication, the full request schema, and data-import details, see [send usage data to the API](https://help.swarmia.com/settings/integrations/ai-coding-tool-integrations/custom-ai-tool-integrations.md#send-usage-data-to-api).

Kiro usage data appears in [Users and licenses](https://help.swarmia.com/features/ai-impact/ai-adoption/users-and-licenses.md) and supports [time-based, low-confidence AI-assisted attribution](https://help.swarmia.com/features/ai-impact/ai-tool-detection-and-filters.md#ai-assisted).


---

# 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/settings/integrations/ai-coding-tool-integrations/custom-ai-tool-integrations/connect-kiro-to-swarmia.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.
