Turn customer notes into problems

Module 1 : What AI already does in your job

Plan du cours

Cette leçon n'est pas encore dans votre langue, la voici donc en anglais.

Petit test

Guess first, no penalty. Which of these is a problem statement, not a feature request?

Customers ask for features. Your job is the problem underneath, because one problem can have a better fix than the one they asked for.

AI is fast at reading five interview notes and grouping what people said. The risks: it turns feature requests into "problems" without changing anything, and it smooths several people's words into one quote nobody said.

So ask for three things with every problem: who has it, the exact quote from the notes, and how many of your interviews mentioned it.

Worked example

A prompt (the message you send the AI):

Here are notes from 5 customer interviews, names removed.

List the problems behind the requests. For each problem:
- who has it (role and situation)
- one exact quote from the notes
- how many of the 5 interviews mention it

Don't add quotes that aren't in the notes. If a request has no clear
problem behind it, list it under "Need to ask".

"Need to ask" turns a gap into your next interview question, instead of a guess.

Complétez les trous

Fill the gaps.

Prompt

From these interview notes, list the problems behind the requests. For each, give . . Put requests with no clear problem under .

Try it

Vos étapes, environ 2 minutes

0 sur 1
  1. 1.Start your one-page PRD (product requirements document: what to build and why). Run the prompt on real notes, names removed, and write the top problem as your Problem section, with its quote and count.2 min

Exercices

Question 1 sur 2

Three customers asked for "export to Excel". What's the best next step?

Tuteur IA

Posez vos questions sur cette leçon et faites-vous guider dans l'exercice « Essayez ». Le tuteur fait partie de Learn Pro.

Voir Learn Pro