> 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/create-deliverables/create-an-executive-summary.md).
# Create an Executive Summary
This page shows you how to turn a finished analysis into a short summary that busy leaders will actually read.
Leaders usually want the short version: what you found, and what to do about it. Evidano gives you two ways to produce that.
{% hint style="info" %}
**What you need:** A completed analysis project (a document or spreadsheet project).
**What you will have at the end:** A short executive summary you can paste into a slide deck or email.
{% endhint %}
## Option 1: Use the built-in summary
When you set up document analysis, the **"Include a summary of your documents"** option (on by default) produces a project summary and an insights narrative on the results page. That's often 80% of an executive summary already — copy it and tighten it.
## Option 2: Generate one with Chat
Open **"Chat to generate custom report/analysis"** and ask for exactly the format you need:
> *"Write a one-page executive summary for a non-technical leadership audience: 3 key findings as headers, 2–3 sentences each, the single most important quote overall, and 3 prioritized recommendations. Plain language, no jargon."*
The standalone chatbot even suggests prompts like *"Write a five-paragraph essay about the top challenges in the document."* See [Chat with your data](/ailyze-docs/analyze-data/chat-with-your-data.md).
## A reliable structure
1. **Context** — one sentence: what was studied and how (sample size, method).
2. **Top findings** — 3–5, each a clear claim with a number and a quote.
3. **Differences that matter** — key [segment](/ailyze-docs/reference/glossary.md#segment) contrasts (see [Compare groups & segments](/ailyze-docs/analyze-data/compare-groups-segments.md)).
4. **Recommendations** — prioritized, tied to findings.
5. **Caveats** — sample limits and how confident you are.
## Make it trustworthy
* **Lead with the decision**, not the methodology.
* **Quantify** ("62% of detractors mentioned onboarding") using the [frequency](/ailyze-docs/reference/glossary.md#frequency) data.
* **One quote per point** — verified against the source.
* **Be honest about limitations** — see [Reporting findings](/ailyze-docs/methods-and-best-practices/reporting-findings.md).
## A realistic example
> **Scenario:** You've analyzed 2,000 NPS (a customer-loyalty score) survey responses. You ask Chat for a one-pager: three findings (onboarding friction, billing confusion, strong support praise), each with a percentage and a quote, plus three recommendations. You check the numbers against the frequency charts and the quotes against the coded table, then drop it into the board deck.
## Next steps
* [Generate a research report](/ailyze-docs/create-deliverables/generate-a-research-report.md)
* [Export & share findings](/ailyze-docs/create-deliverables/export-and-share-findings.md)
* [Reporting findings](/ailyze-docs/methods-and-best-practices/reporting-findings.md)
---
# 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/create-deliverables/create-an-executive-summary.md?ask=&goal=
```
`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.