Your reviews are full of feature requests, but they're spread across hundreds of reviews, several platforms, and different languages. Reading them one by one makes it hard to tell which requests are common and which are just loud. Your AI assistant can group them into themes, count them, and show you who's asking. In this article, you'll learn what this request returns, how to ask for it, and how to use the results in your roadmap.
Overview
When you ask about feature requests, your assistant returns:
- Themes ranked by how many users asked, with a count for each
- Two or three quotes per theme, taken word for word from real reviews
- Movement against the previous month, so you can see which requests are growing
- The average rating of the people asking
The results are formatted so you can paste them straight into a roadmap doc. This is a read-only request. Nothing in your account changes.
Why the rating of the people asking matters
The same request means something different depending on who makes it. A request from users rating you 5 stars is coming from fans who want more. A request from users rating you 1 or 2 stars is often coming from people who are about to leave. The average rating helps you tell the two apart.
How to ask
Once AppFollow MCP is connected to your AI assistant, you can ask in plain language. For example:
What did users ask us to build last month, ranked by how many asked?More things to ask
- "Top 10 feature requests across both platforms in the last 90 days, one line each."
- "Which requests are growing fastest quarter over quarter?"
- "Do users asking for [feature] rate us above or below our average?"
- "Pull every review mentioning 'dark mode' over the last 6 months and tell me whether the ask has changed."
💡 Haven't connected yet? See AppFollow MCP and AI Toolkit for setup steps for each supported client.
Reading the results
| Item | What it means |
|---|---|
| Theme | A group of reviews asking for the same thing, even if they word it differently |
| Count | How many reviews in the period ask for it |
| Change | How the count moved compared with the previous period |
| Avg. rating | The average star rating of the reviews asking for it |
| Quotes | Examples from real reviews, so you can see how users describe it |
F.A.Q.
Does it include reviews in other languages?
Yes. Requests are grouped by meaning, not by wording, so reviews in different languages can land in the same theme. Ask the assistant to translate the quotes if you need them in one language.
Can I focus on one feature?
Yes. Name the feature or a keyword, and the assistant pulls every review that mentions it over the period you choose.
Why does a longer period take more time?
The assistant reads every review in the period, so a 90-day window with thousands of reviews takes longer and uses more credits than a single month.