> 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/common-research-workflows/analyze-customer-feedback.md).

# Analyze Customer Feedback

This page shows you how to turn customer feedback — reviews, support tickets, and survey comments — into clear [themes](/ailyze-docs/reference/glossary.md#theme), quotes, and a summary you can share.

{% hint style="info" %}
**What you need:** the Free Plan or higher, plus your feedback as a spreadsheet (XLSX or CSV), a document (DOCX or PDF), or a web link you collect first.

**What you will have at the end:** a set of ranked themes with quotes and [segment](/ailyze-docs/reference/glossary.md#segment) comparisons you can export.
{% endhint %}

Customer feedback comes in many shapes. The trick is matching the *format* to the right workflow.

## Step 1: Pick the workflow that matches your data

| Your feedback is…                                                                               | Use                                                   | Why                                                             |
| ----------------------------------------------------------------------------------------------- | ----------------------------------------------------- | --------------------------------------------------------------- |
| A **spreadsheet** (an NPS (a customer-loyalty score) export, ticket dump, or feedback-form CSV) | **"Analyze xlsx/csv files"**                          | Code the comment column and compare by plan, region, or channel |
| **Documents** (interview write-ups, long-form feedback)                                         | **"Analyze docx/pdf files"**                          | Turn rich text into themes with quotes                          |
| **Live on the web** (app-store reviews, marketplace reviews, social comments)                   | Collect it first with **"Get Social Media Web Data"** | Download the data, then analyze the spreadsheet                 |
| **Recorded calls**                                                                              | **"Transcribe Audio/Video"** first                    | Then analyze the transcript                                     |

Most customer-experience teams have a spreadsheet, so this guide follows the **xlsx/csv** path.

## Step 2: Set up your analysis

1. Start **"Analyze xlsx/csv files"** and upload your export. Use one XLSX or CSV file per project.
2. At **"Choose the type of Analysis"**, pick **"Analyze text, numerical, categorical, etc. survey data across all columns"** for a full survey dashboard, or **"Analyze text responses in selected columns"** to focus on the comment field.
3. In **"Configure Column Types"**, drag your routing columns — channel, plan, region, or a CSAT (a customer-satisfaction score) or NPS score band — into **"Segments"**. This is what turns "people are unhappy" into "*enterprise* users on the *mobile* channel are unhappy about *onboarding*."
4. Let Evidano generate [themes](/ailyze-docs/reference/glossary.md#theme) for the comment column, then rename them to your team's language if you like.
5. Click **"Create Project and Start Analysis"**.

<figure><img src="/files/ZIVRsXgwbmhAQjJbR40t" alt="Setting up a customer-feedback spreadsheet analysis"><figcaption></figcaption></figure>

{% hint style="info" %}
**Tip:** Add an instruction such as *"This is post-support CSAT feedback; focus on resolution speed, agent helpfulness, and product issues."* It sharpens the themes.
{% endhint %}

## Step 3: Read your results

* **Themes and** [**sub-themes**](/ailyze-docs/reference/glossary.md#sub-theme) of pain points and praise, with [frequencies](/ailyze-docs/reference/glossary.md#frequency) so you can prioritize by volume.
* **A quote for each theme** — the exact quotes (verbatims) to drop into a deck or QBR (a quarterly business review).
* **Segment comparisons** — which customers are affected most.
* **A coded data table** — every comment tagged and exportable to CSV, so you can pivot it yourself.

<figure><img src="/files/A9xsjkUQCtoK3OFns1Kh" alt="Customer-feedback themes with frequencies and quotes"><figcaption></figcaption></figure>

See [How to read your results](/ailyze-docs/analyze-data/how-to-read-your-results.md) for a tour of every panel.

## Step 4: Turn it into a deliverable

* Click **"Chat to generate report or chart"** and ask: *"Give me the top 5 pain points with a representative quote and the % of responses for each."*
* **"Download as DOCX"** for a written report, or **"Download as CSV"** for your own tool.
* Write a short leadership summary — see [Create an executive summary](/ailyze-docs/create-deliverables/create-an-executive-summary.md).

{% hint style="info" %}
**Heads-up:** Downloading a report and adding collaborators need the **"Pro Plan"**. See [Plans, Limits & Credits](/ailyze-docs/reference/plans-limits-and-credits.md) for what each plan includes.
{% endhint %}

## A realistic example

> **Scenario:** You export **5,000 support tickets** with columns for product area, plan, and the customer's message. You pick **"Analyze text responses in selected columns"** on the message field, drag product area and plan into **"Segments"**, and let Evidano theme the issues. In about 20 minutes you have the top recurring problems by product area, ranked by volume, with quotes — plus a Chat answer to *"What's driving contacts about billing this month?"*

## Next steps

* [Analyze open-ended survey responses](/ailyze-docs/common-research-workflows/analyze-open-ended-survey-responses.md)
* [Compare groups and segments](/ailyze-docs/analyze-data/compare-groups-segments.md)
* [How to read your results](/ailyze-docs/analyze-data/how-to-read-your-results.md)
* [Create an executive summary](/ailyze-docs/create-deliverables/create-an-executive-summary.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/common-research-workflows/analyze-customer-feedback.md?ask=<question>&goal=<endgoal>
```

`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.