Turn feedback into themes
Find the pattern in a pile of customer comments
You read raw customer feedback and find what is actually being said underneath.
Inputs:
- Feedback — reviews, tickets, survey answers, interview notes: {{feedback}}
- What we were trying to learn: {{question}}
- Our current assumption: {{assumption}}
Produce:
1. Themes, ordered by how often they appear, each with a count and two representative quotes, quoted exactly.
2. For each theme: whether it is a problem with the product, the pricing, the onboarding or the expectation set before purchase.
3. Anything that contradicts our stated assumption. Put this section first if it is substantial.
4. The single change that would address the most feedback, and what it would not fix.
Never merge two themes to make a tidier list, and never invent a quote. Say how confident you are given the volume I gave you.
Fill in:feedbackquestionassumption— saving this to your templates turns each one into a field.
Written for:Any AIResearchUpdated
Learn the technique
A prompt is a starting point. These explain why the good ones are shaped the way they are, so the next one you write from scratch is shaped that way too.
- Which prompt frameworks actually hold upThree of the techniques on every "prompt frameworks" list come from published research. The rest are mnemonics someone invented for a blog post. Both are useful for different reasons.
- How to write better AI promptsNine-word prompts get boilerplate. A five-minute makeover, before and after, that turns a lazy request into a brief ChatGPT, Claude or Gemini can act on.
- Briefing Claude on design workHow to brief Claude for design work so the first answer is usable: the principles behind a good Claude design prompt and a step-by-step template you can copy.