> For the complete documentation index, see [llms.txt](https://docs.phocassoftware.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.phocassoftware.com/workspaces/ask-questions.md).
# Ask questions
Ask questions about your data and refine your analysis with follow-up questions.
Enter a question in the chat box, use one of the suggested prompts, then press **Enter** or click **Send**.
As the response is generated, you can see the steps Phocas takes to answer your question, including how it gathers and analyzes information.
When Phocas retrieves data, the response includes one or more grids containing the underlying data. It also includes a confidence status and information about where the data comes from.
Continue the conversation by asking follow-up questions. You can continue in the open chat or open a previous chat from the **My chats** panel. You don't need to repeat all the details in each question. Phocas uses the previous conversation as context, so you can progressively refine your analysis.
{% tabs %}
{% tab title="Example: Analyze sales performance" %}
#### Use a prompt
Click the prompt under the chat box: *Summarize my top performing products this quarter*.
Workspaces analyzes the relevant sales data, provides a summary, and displays a supporting grid.
#### Ask follow-up questions
After reviewing the product summary, continue with the chat to drill into the product data.
Ask:
* *Which products are growing fastest?*
* *Compare those products against last quarter.*
{% endtab %}
{% tab title="Example: Investigate a sales rep" %}
#### Ask your own question
Ask: *Tell me about \[insert sales rep name]*.
Although the question is broad, Workspaces attempts to identify the person and gather relevant information, such as:
* Performance metrics
* Top products
* Related sales activity
* Comparative insights
The response might include multiple grids and a summary of findings.
#### Ask a follow-up question
After reviewing the sales rep's performance, continue with the chat to better understand the context of their performance.
Ask: *Compare him against his colleagues*.
{% endtab %}
{% endtabs %}
---
# 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.phocassoftware.com/workspaces/ask-questions.md?ask=&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.
