# Report

The Report feature in Zerve transforms your data notebooks from static workspaces into interactive, shareable insights. By bridging the gap between deep technical analysis and stakeholder friendly summaries, it allows you to communicate findings instantly without any extra work.

### How to create a report

**Automated Generation:** Instantly generate a structured report based on the blocks and outputs within your notebook. Zerve’s engine analyzes your charts, tables, and code logic to create a cohesive summary of your work.

**Prompt Based Customization:** Take control of the narrative by providing specific prompts. You can instruct the agent to focus on specific KPIs, explain certain anomalies, or format the report for a particular audience.

### Ask Questions

Reports in Zerve are not static documents. You can interact with your report using the built-in AI agent. Ask follow-up questions like *"Why did churn spike in October?"* or *"What was the correlation between ad spend and conversions?"* The agent will query the underlying analysis in the backend to provide accurate, data-driven answers.

You can also share the report with your team and all of them can ask questions to the agent.

The following video shows how a report can be generated.

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIQKNeqjEeOp9UwUcB9R9%2Fuploads%2FrqejU9qYiVMyaueIjGpv%2FReport%20Final.mp4?alt=media&token=1dd9a21a-77d2-4c11-905a-3ec53464c5c5>" %}


---

# Agent Instructions: 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:

```
GET https://docs.zerve.ai/guide/notebook-view/report.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.
