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

# Reports

Reports holds a set of pre-built dashboards over the same trace and observation data you can browse in Observability, aggregated so you see patterns rather than individual requests.

Three ship with the platform.

* **Cost** breaks spending down by model, environment, user, and use case, with percentile costs per trace and per observation to separate typical spend from outliers.
* **Usage Management** tracks volume: traces, observations, and numeric and categorical scores, over time and by environment.
* **Latency** covers response time by use case, level, model, and user, alongside time to first token and output throughput per model.

A date range and filters apply across a whole dashboard, and individual widgets can be downloaded on their own.

{% hint style="info" %}
Reports aggregates LLM activity across your project. For a live snapshot scoped to selected agents, see [Home](/home.md). To inspect one request, see [Observability](/governance/observability.md). For container traffic and resource use, see [Analytics](/governance/analytics.md).
{% endhint %}


---

# 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.interactive.ai/governance/reports.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.