> For the complete documentation index, see [llms.txt](https://docs.praiz.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.praiz.io/query-and-analyze/ask-praiz.md).

# Ask Praiz

Ask a question about one specific call and get an answer grounded in what was said.

## Use Ask Praiz

1. In "My Recordings", open the call you are interested in.
2. In the right-hand panel, below the video, open the "Ask Praiz" tab.
3. Type your question and confirm.

![Ask Praiz tab on a call page](https://3785996597-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FU54oKzNb3EyinriyUP5P%2Fuploads%2FvbwqczfgK1YzFbvcNeb5%2F14-recording-ask-praiz.png?alt=media)

What to expect: Ask Praiz shows an answer grounded in the transcript of that call. You do not have to listen to the recording again. Under each answer, "Copy" copies it as clean text, for example to paste it into an email.

Example questions:

* Which objections did the prospect raise?
* Which competitors were mentioned, and in what context?
* What next steps were agreed?
* Was the budget discussed?
* Draft a follow-up email from this call.

## Scope: one call at a time

Ask Praiz works on a single conversation.

| You want to                                        | Use                                            |
| -------------------------------------------------- | ---------------------------------------------- |
| Dig into one point on one specific call            | Ask Praiz                                      |
| Surface trends across all of your conversations    | [Insights](/query-and-analyze/insights.md)     |
| Query your database from Claude, ChatGPT or Gemini | [MCP server](/query-and-analyze/mcp-server.md) |

## Ask Praiz or an agent

* Ask Praiz answers a one-off question about this call. The answer is not kept in your conversational database.
* An agent applies every time. It fills in the same fields on every call. Its output feeds your conversational database. See [What is an agent?](/ai-agents/what-is-an-agent.md).