Dashboard exports work well for a quick look, but they stop at 10,000 rows. If you want to analyze years of reviews, join them with your own data, or load them into a data warehouse, you need the full history. Your AI assistant can pull every review for the period you choose and save it to a file. In this article, you'll learn what the export includes, how to ask for it, and what you can do with the data once you have it.
Overview
When you ask for a full export, your assistant pulls every review in the period, beyond the 10,000-row limit on dashboard exports. Each row includes:
| Field | What it contains |
|---|---|
| Rating | The star rating, from 1 to 5 |
| Title and body | The full review text |
| Author and date | Who wrote it and when |
| Platform and country | Where the review was posted |
| Language | The language of the review |
| App version | The version the review was written on |
| Reply | Whether you replied, and the reply text |
The assistant writes the data to a file, such as a CSV, instead of pasting it into the conversation. That's what makes large exports with tens of thousands of reviews practical: you get something you can query, not a long transcript. This is a read-only request. Nothing in your account changes.
Saving to a file depends on your AI client. Clients that can create files, such as desktop apps and coding tools, handle large exports best.
What to do with the data
- Join it with your own data. Reviews carry the app version and country, and so do your subscription events and support tickets. Together, they can show whether users who complained about something actually cancelled, or whether the countries reporting bugs are the ones you're losing.
- Use your own categories. Sort reviews into the topics your team already uses, and re-run the sorting whenever those topics change, without pulling the data again.
- Look further back. Years of releases in one table show how complaints shifted over time, further back than any dashboard view.
How to ask
Once AppFollow MCP is connected to your AI assistant, you can ask in plain language. For example:
Pull every review for [app] since January and save it as a CSV we can load into our warehouse.More things to ask
- "How many reviews are in that window before we pull them?"
- "Export all reviews for our five apps for the last two years, one CSV per app."
- "Same export, plus a column flagging which ones we answered."
- "Export [competitor]'s reviews for the last year so we can compare the complaint mix."
💡 Haven't connected yet? See AppFollow MCP and AI Toolkit for setup steps for each supported client.
F.A.Q.
How many credits does an export use?
The assistant reads reviews in pages of 100, and each page uses credits. Ask how many reviews are in the period before you start, so you know how big the export will be. For the cost of each request, see Methods cost and availability.
Why are some countries empty for Google Play reviews?
Google Play only shares review countries when the right data connection is set up. See Google Play: Reviews Country Data Connection.
Can I export a competitor's reviews?
Yes, as long as the competitor is tracked in one of your workspaces. Name it in your request.