# A thousand answers, five themes.

> Febaso reads every open answer and groups them into themes with counts and verbatim quotes, across languages. Every summary can be traced to the answer.

Web page: https://febaso.com/features/themes-and-analysis · Updated: 2026-10-21

Febaso reads every open answer, groups them into themes with counts and verbatim quotes, and shows what weighs most.

- Every theme with count and quotes
- All languages in one overview
- Every summary traceable

## From a pile of answers to what's going on.

1. **Every answer is read.** The long ones, the short ones and those in another language. Nothing is left because there was no time.
2. **Similar answers come together.** As themes with a name, the number of people who raised it and the verbatim quotes below.
3. **You look, check and decide.** Open a theme, read the answers behind it and choose what to do. The AI organises, you decide.

## An overview you can check.

- **Themes.** A name, the number of people who raised it and the verbatim quotes.
- **Checking.** From every theme to the answers behind it. Every summary can be traced to the answer itself.
- **Languages.** A Polish and a Dutch answer about the same problem end up in one theme. You read it all in yours, with the original next to it.
- **While it runs.** The themes are there while answers come in, so you can adjust before the round is over.
- **Views.** As a list, as a board with what still needs to happen, or as a map of themes.
- **Per group.** Ask about the department, the course or the region in the conversation, and you see the themes per group.
- **Across rounds.** Ask the same questions every round and follow whether a theme grows or disappears.
- **A decision attached.** Per theme you see whether it is still waiting for a decision, and whoever raised it can get an update.

## Answers come in, the themes take shape.

Answer an interview as a customer and see what happens to your answer. Ten taps, with made-up data, and then you look around yourself.

### What one round yields (Example data)

Northwind Summit 2026 · Northwind. Northwind, Marieke and every answer here are made up for this demo.

| Theme | Raised by | In their words |
| --- | --- | --- |
| Sessions: too many overlap | 186 attendees | "Two talks I wanted ran at the same time. I had to choose, and I picked wrong." |
| Programme: published late | 23 attendees | "The schedule came out two days before." |
| Lunch: long queues | 142 attendees | "Half an hour in line for lunch." |
| Networking: too little time | 97 attendees | "Great people, too little time to talk." |
| Speakers: worth the trip | 88 attendees | "The keynote alone was worth the trip." |

## Reading takes time. The overview makes the difference.

| By hand | With Febaso |
| --- | --- |
| Hundreds of open answers in a spreadsheet, and no time to read them all. | Every answer read and grouped into themes, with the count and the verbatim quotes next to it. |
| A score shows that something is going on, not what. | The why, in the respondent's own words, with a follow-up when an answer stays vague. |
| Answers in other languages stay unread, or go through a translation tool. | All languages in one theme, with the original next to your translation. |
| The analysis arrives weeks after collecting, when the moment has passed. | The themes while it runs, so you can adjust. |
| Comparing this year with last year means starting over. | The same questions every round, and you see whether a theme grows or disappears. |

## The AI organises, you decide.

- **Checkable, not a black box.** Every theme shows how many people raised it and what they said verbatim. In doubt, open the theme and read the answers.
- **Counts are not statistics.** A theme with 42 mentions shows where most words are, not that 42 of every hundred people think so. With small or non-representative groups, read it as a signal.
- **What you do with it stays yours.** Febaso shows what is going on. What it means and what you do about it is for you to weigh with your other sources.
- **Small is small.** With fifteen answers you read everything yourself. It pays off with dozens to hundreds of answers and across several rounds.

## Every question with open answers.

- [NPS](https://febaso.com/use-cases/nps.md): The score, and why
- [Customer satisfaction (CSAT)](https://febaso.com/use-cases/customer-satisfaction-csat.md): CSAT with follow-up questions
- [Employee engagement (eNPS)](https://febaso.com/use-cases/employee-engagement-enps.md): Engagement and eNPS, anonymous
- [Member feedback](https://febaso.com/use-cases/member-feedback.md): For associations
- [Course evaluation](https://febaso.com/use-cases/course-evaluation.md): Courses and classes

## Privacy and trust

- **Processing in the EU.** And never used to train AI models.
- **Anonymous when you choose.** You choose per interview whether answers are anonymous. Anonymous means you never see who said what.
- **Open about the AI.** Respondents know from the first message that they are talking to an AI.
- **Traceable.** Every theme shows the count and the verbatim quotes.

[Read how we handle privacy](https://febaso.com/privacy)

## Frequently asked questions

### How do I know the themes are right?

You don't have to take our word for it. Every theme shows how many people raised it and their verbatim quotes, and you can click through to the answers behind it. A spot check of a few quotes shows right away whether a theme holds.

### How many answers do I need?

With a few dozen answers themes start to show, and it pays off more the more there are. With fifteen answers you're better off reading them yourself.

### Does it work for answers in other languages?

Yes. Answers in different languages end up in one theme, and you read them in your language with the original next to it.

### Can I look per department, course or region?

Yes. Ask in the conversation which group someone belongs to, and you see the themes per group. In a very small group an answer can be recognisable by its content; we look at that together when setting up.

### Can I compare themes across rounds?

Yes. Ask the same questions every round, and you see whether a theme grows, shrinks or disappears.

### What happens to the answers?

They are processed within the EU and never used to train AI models. Every customer signs a data processing agreement, and data is deleted on request.

## Let your answers say something.

In a thirty-minute intro I show Febaso live, with your kind of questions. Or try the demo first.

- [Book an intro](https://febaso.com/features/themes-and-analysis#contact)