Lesson 200 · 3 min
Reading customer feedback at scale
Paste a batch of reviews or survey answers and ask AI to group them into themes with counts and real quotes.
Reading two hundred reviews one by one is slow, and you tend to remember the angriest ones. AI can sort them into themes, like delivery, price or staff, and count how often each comes up.
Ask for a quote from a real customer under each theme. Quotes keep the summary honest and let you check that a theme is real and not something the model invented.
Counts from a chatbot can be off, especially with large batches. For decisions that matter, check a sample by hand or use a spreadsheet to tally the themes it found.
Remove names, phone numbers and order IDs before pasting, unless your company has approved the tool for customer data.
Do it now
Find the top three complaints
- 1. Export 30 to 100 recent reviews or survey answers.
- 2. Remove personal details.
- 3. Run the prompt below, then read five comments from the top theme yourself.
Here are customer comments, one per line. Group them into 4 to 7 themes. For each theme give: a short name, roughly how many comments fit, whether they are mostly positive or negative, and 2 exact quotes. Then suggest the one change that would fix the most complaints. [PASTE COMMENTS]
Quick check
Keep going
Next →Writing a leave requestWords from this lesson
- Classifier
- A model that sorts things into groups, such as spam or not spam, or which plant is in a photo.
- Data privacy
- Keeping personal or confidential information under control, including deciding what you type into AI tools and where it is stored.
- Hallucination
- When an AI states something false with confidence, such as a made-up fact, quote or source.