> For the complete documentation index, see [llms.txt](https://ailyze.gitbook.io/ailyze-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ailyze.gitbook.io/ailyze-docs/analyze-data/chat-with-your-data.md).

# Chat With Your Data

This page shows you how to ask questions about your data in plain language and turn the answers into report-ready text.

{% hint style="info" %}
**What you need:** a Pro plan (chat is a Pro feature), and either a project you've already analyzed or files to upload.

**What you will have at the end:** quick summaries, targeted quotes, and draft paragraphs — plus custom charts in spreadsheet projects — that you can paste straight into your report.
{% endhint %}

Evidano's chat lets you ask about your data in a back-and-forth conversation. You can open it in a few places — same idea, slightly different scope.

## Where you can chat

| Where                        | Scoped to                                                            | Open it via                                                                                                         |
| ---------------------------- | -------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- |
| **In a document project**    | That project's transcripts and analysis                              | **"Chat to generate custom report/analysis"** (Action bar or floating button)                                       |
| **In a spreadsheet project** | That project's data and analysis                                     | **"Chat to generate report or chart"**                                                                              |
| **On a single theme**        | One [theme](/ailyze-docs/reference/glossary.md#theme) and its quotes | **"Chat with this theme"** — a Pro-only shortcut inside a theme (Free shows the tooltip *"Upgrade to Pro to chat"*) |
| **On its own**               | Files you upload or select                                           | The **"Chat with Data"** card on your dashboard                                                                     |

Wherever you open it, the chat panel is headed **"AI ChatBot"**.

<figure><img src="/files/mQ8782n0T6d8j9f4EB95" alt="Evidano chat panel answering a question about the data"><figcaption></figcaption></figure>

## What it's great at

* **Summaries:** *"Summarize the top 3 challenges in two paragraphs with quotes cited."*
* **Reframing for an audience:** *"Write a 5-paragraph executive summary of the main findings."*
* **Targeted pulls:** *"List every quote about pricing from enterprise participants."*
* **Custom charts** (in spreadsheet projects): *"Make a bar chart of cancellation reasons by plan."*
* **Pressure-testing:** *"What evidence contradicts the 'onboarding is confusing' theme?"*

The standalone chat greets you with example prompts like *"What were the top challenges in two paragraphs with relevant quotes cited?"*

## What it's *not* for

Evidano itself flags this in the chat: it's *"better for quick summaries of the AI report, rather than in-depth new analysis of your data. Use 'Add Question/Theme' for deep analysis. Review insights carefully."*

So:

* For **new, rigorous analysis**, use **Add Theme/Question** (documents) or run a fresh analysis — not chat.
* **Always verify** quotes and claims against the source before publishing.

## Chat with your own files

1. Open the **"Chat with Data"** card on your dashboard.
2. Use the **"+"** menu to attach files (up to **3**), or select files you've uploaded before, so the chat has something to read.
3. Ask your question. Answers **stream** in as they're written.
4. Use the **conversation sidebar** to revisit, rename, share, or delete past chats, and the **prompt library** for ready-made research prompts.
5. **Share** a conversation by link, or go **full screen** for long sessions.

<figure><img src="/files/pkkISZZP3df1AwlgJWTH" alt="Attaching files to a standalone chat with the plus menu"><figcaption></figcaption></figure>

{% hint style="info" %}
**Tips for better answers**

* **Be specific about format:** "two paragraphs", "a bulleted list of 5", "with quotes and the % of responses".
* **Name the scope:** which theme, which segment, which question.
* **Ask for evidence:** request quotes and counts, then check them.
* **Iterate:** refine the prompt rather than starting over.
  {% endhint %}

## Access and cost

The AI ChatBot is a **Pro** feature. On Free accounts, the chat shows an upgrade prompt instead of sending your message.

{% hint style="info" %}
For what's included on each plan, see [Plans, Limits & Credits](/ailyze-docs/reference/plans-limits-and-credits.md).
{% endhint %}

## A realistic example

> **Scenario:** After analyzing 40 interviews, open chat and ask: *"Draft the findings section: top 4 themes, one verbatim quote each, \~120 words per theme, neutral academic tone."* Paste the draft into your report, then verify each quote against the transcript before finalizing.

## Next steps

* [How to read your results](/ailyze-docs/analyze-data/how-to-read-your-results.md) — understand what the chat is drawing from.
* [Create an executive summary](/ailyze-docs/create-deliverables/create-an-executive-summary.md) — turn chat drafts into a polished summary.
* [Build a codebook](/ailyze-docs/analyze-data/build-a-codebook.md) — refine the themes and codes behind your data.


---

# 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://ailyze.gitbook.io/ailyze-docs/analyze-data/chat-with-your-data.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.
