> 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/how-to-read-your-results.md).
# How to Read Your Results
This page shows you how to read an Evidano analysis results page. In plain language, it helps you interpret [themes](/ailyze-docs/reference/glossary.md#theme), [codebooks](/ailyze-docs/reference/glossary.md#codebook), charts, and quotes, and know which button does what.
The results page holds a lot of information, and it's dense the first time. Think of this guide as a glossary and a map for the **document** and **spreadsheet** results pages. Keep it open the first few times.
## The vocabulary
| Term | What it means in Evidano |
| ---------------------------------- | ---------------------------------------------------------------------------------------------------------------------- |
| **Theme** | A top-level pattern in your data (e.g. *"Onboarding friction"*). |
| **Sub-theme / Code** | A specific idea within a theme (e.g. *"Confusing first screen"*). Evidano uses "sub-theme" and "code" interchangeably. |
| **Codebook** | The full, structured set of themes → sub-themes/codes used to label your data. |
| **Coding / labeling** | Tagging each excerpt or row with the codes it expresses. |
| **Quote** | A verbatim excerpt that illustrates a code. |
| **Segment** | A group you compare across (department, region, plan, rating band…). |
| **Synthesis / Insights / Summary** | AI-written narrative interpreting the data. |
| **Frequency** | How often a theme/code appears — used to prioritize. |
## The document results page
Top to bottom:
1. **Header** — project name, **ID**, and a **document count** chip you can click to see which files are included. Pencil = rename.
2. **Action bar** — your tools (see the **What you can do next** section below).
3. **Insights** — the headline findings across the whole project.
4. **Codebook table** — themes → sub-themes/codes with **frequency** columns. This is your at-a-glance map of *what was found and how often.*
5. **Project summary** — an overview of the documents.
6. **Word-frequency visualization** — a bar chart + word cloud of common terms.
7. **Segment data overview** — appears if you compared segments.
8. **Themes / Questions** — the heart of the report, one expandable section each.
### Inside a theme
Expanding a theme reveals:
* **Summary across all files** — the AI's synthesis of the theme.
* **Codes & key quotes** — quotes grouped by code (with **CSV export** and a chat button), plus **Visualizations** (Hierarchy Graph, Co-occurrence Network) and a **Table**.
* **Comparison across segments** — how the theme differs by group (if enabled).
* **Summary of individual files** — per-document detail.
### Making sense of the charts
* **Frequency bar / pie** — which codes dominate. Toggle **Percentage** and **Put segments on y-axis** to compare groups.
* **Hierarchy graph** — how sub-themes nest under themes.
* **Co-occurrence network** — which themes tend to appear *together* (great for spotting relationships, e.g. *price* ↔ *trust*).
* **Word cloud** — quick gist of frequent terms (not a substitute for themes).
## Spreadsheet results — two pages
### The survey dashboard
A per-column summary of the whole survey, grouped into **Text / Numerical / Categorical / Segment / Respondent ID**. Each column has:
* **Visualization** — a chart with a **Segment** selector and **Download CSV/PNG**.
* **Analysis** — an AI narrative, with **"View More Analysis"** to open that column's per-column results page (the deep dive for that question).
### The per-column results page
The deep dive for one open-ended question:
* **Codebook** and **Synthesis**
* **Frequency Bar Chart (Themes)** and **(Sub-themes)**
* **Hierarchy Graph**, **Co-occurrence Network**, **Word Frequency Visualizer**
* **Data Coded with AI Themes & Sub-themes** — a table with tabs: *AI Labels as List*, *AI Labels as Checklist (with code justifications)*, *Theme & Sub-theme Frequencies*
* **Elaboration of Themes & Sub-themes** — per-theme cards with quotes
## What you can do next
Both document and spreadsheet results pages share an **Action** bar:
| Button | Purpose |
| ------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| **Chat to generate custom report/analysis** (or "…report or chart") | Ask questions, build summaries and charts → [Chat with your data](/ailyze-docs/analyze-data/chat-with-your-data.md) |
| **Download as DOCX / XLSX / CSV** (Word, Excel, or spreadsheet) | Export the report or data → [Generate a research report](/ailyze-docs/create-deliverables/generate-a-research-report.md) |
| **Share as Webpage** | Public read-only link *(Pro)* → [Export & share findings](/ailyze-docs/create-deliverables/export-and-share-findings.md) |
| **Add File / Theme / Question** (documents) | Extend the analysis *(Pro)* |
| **Edit Codebook** | Refine themes and codes *(Pro)* → [Build a codebook](/ailyze-docs/analyze-data/build-a-codebook.md) |
| **Calculate AI Accuracy** | Check coding reliability *(Pro)* |
{% hint style="info" %}
Free accounts see most actions disabled with **"Only allowed for paid users."** While analysis is still running, actions are disabled with an "in progress" note, and you'll see **partial results** with a banner.
{% endhint %}
## How to actually interpret it (a quick method)
1. **Start with the Codebook table / Insights** for the big picture.
2. **Sort by frequency** to find what matters most — but don't ignore rare, high-signal themes.
3. **Open the top 3–4 themes**, read the summary, and pull 1–2 quotes each.
4. **Check segment comparisons** for "who" differences.
5. **Use Chat** to draft your write-up and pressure-test ("Is there evidence against this theme?").
6. **Verify quotes** against the source before publishing — always.
{% hint style="info" %}
Evidano's in-app chatbot itself reminds you: it's *"better for quick summaries of the AI report, rather than in-depth new analysis."* Use **Add Theme/Question** for genuinely new analysis, and review insights carefully.
{% endhint %}
## Next steps
* [Discover themes and patterns](/ailyze-docs/analyze-data/discover-themes-and-patterns.md) — go deeper into the big ideas in your data.
* [Chat with your data](/ailyze-docs/analyze-data/chat-with-your-data.md) — ask questions and draft your write-up.
* [Analysis issues](/ailyze-docs/troubleshooting/analysis-issues.md) — if your results look off or are missing.
---
# 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/how-to-read-your-results.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.