> For the complete documentation index, see [llms.txt](https://support.meetuma.ai/uma-knowledgebase/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://support.meetuma.ai/uma-knowledgebase/data-and-reporting/analytics-pro/ai/ai-chart-explain.md).

# AI Chart Explain 🤖

<figure><img src="/files/C1zasRq65icHivNuHY4a" alt=""><figcaption></figcaption></figure>

### Overview

AI Chart Explain provides a one-click natural-language interpretation of any chart in Analytics Pro. The feature uses a vision-capable language model that reads the rendered chart together with a sample of the underlying data, and returns a concise explanation of what the chart shows, why it might be doing so, and what to investigate next.

Use it to:

* Generate talking points for executive briefings and reviews
* Produce written commentary for monthly facilities reports
* Quickly understand unfamiliar charts without manual analysis
* Provide context to non-technical stakeholders

***

### How to Use It

1. Open any chart in any Analytics Pro dashboard.
2. Click the **Explain with AI** icon (the lightning / sparkle icon) in the chart header.
3. The explanation appears in a panel below the chart while it generates, with a skeleton loader.
4. Once complete, the explanation is rendered as formatted Markdown and includes a copy-to-clipboard button.
5. Hide or minimise the panel when you have read it; the result remains attached to the chart for the rest of the session.

***

### What the Explanation Contains

Every explanation is contextualised by the filters currently applied to the chart (building, floor, date range, resource type) and includes:

* A summary of what the chart conveys
* Trend analysis: direction, notable points, and anomalies
* Likely causes for the observed pattern
* Suggested next steps for investigation or action

***

### Example

<figure><img src="/files/iMm23C3GSMvvfEJ640SI" alt=""><figcaption></figcaption></figure>

***

### Availability

<table><thead><tr><th>License Tier</th><th width="301">AI Explain Available On</th></tr></thead><tbody><tr><td>BasicAI</td><td>Free analytics charts</td></tr><tr><td>AnalyticsPro</td><td>Not included</td></tr><tr><td>Enterprise</td><td>All charts (free + Pro)</td></tr></tbody></table>

***

### Output Features

* **Markdown formatting** — explanations support emphasis, bullet lists, and headings
* **Copy to clipboard** — one-click copy for use in emails, reports, or chat
* **Hide / minimise** — collapse the panel without losing the result
* **Persistent within the session** — re-open the same chart to retrieve the same explanation
* **Saved with reports** — explanations generated within the Reports feature are stored alongside the chart in the saved report

***

### Best Practices

* AI Explain works best when you already see something interesting and want a structured second opinion. It is less useful for charts whose data is flat or empty.
* The model sees only the rendered chart and a sample of the data, not your private notes or other dashboards. Adjust filters and re-explain to change the focus.
* If the explanation seems generic, narrow the date range and re-run — context tightens the response.
* Treat AI Explain output as a draft commentary, not a final report. Always validate before circulating externally.


---

# 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, and the optional `goal` query parameter:

```
GET https://support.meetuma.ai/uma-knowledgebase/data-and-reporting/analytics-pro/ai/ai-chart-explain.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.
