Prepare the monthly App Store and Google Play review summary, from ChatGPT or Claude
Rating per store, rising topics, unanswered reviews and reply delay: your AI prepares the monthly review summary of your apps, backed by numbers.
Published on November 1, 2026
In short
- With Persyst’s Google Play and App Store Connect connectors, your assistant prepares the monthly review summary: ratings, volumes, topics, replies.
- The numbers are computed over all imported reviews, not over the page of reviews the assistant read.
- Leadership or support get the summary with no export and no spreadsheet to maintain.
Summarize October’s reviews for both our apps, compared with September.
October: 412 reviews (+18%), average rating 4.1 on Google Play and 4.3 on the App Store, stable. The rising topic is the subscription price: 31 reviews against 9 in September, after the October 1 increase. The reply rate drops from 71% to 54%, and the average delay goes from 20 to 41 hours: 23 one- and two-star reviews remain unanswered, 15 of them on Google Play.
Sources consulted
- Google Play reviews · statistics by month
- App Store reviews · statistics by month
- Google Play and App Store reviews · search
The problem: a monthly review that takes half a day
Every month, someone exports reviews from both consoles, pastes them into a spreadsheet, computes ratings, counts unanswered reviews and rereads the latest ones to find the topics. The result arrives late, and nobody has time to check whether it is right.
An AI assistant prepares this summary in one conversation, as long as it can read the reviews and compute their statistics.
What the assistant does, step by step
With Persyst’s Google Play and App Store Connect connectors, the request “Summarize October’s reviews” runs this reasoning:
- Compute the indicators by month (
get_play_review_stats,get_app_store_review_stats): review count, average rating, star distribution, reply rate and delay. - Spot the month’s topics by reading the period’s reviews (
list_play_reviews,list_app_store_reviews). - Compare topics month over month with targeted searches (
search_play_reviews,search_app_store_reviews). - List unanswered negative reviews (reply filter), for support.
Asking the right question
- Set the format: “five lines for leadership, then the detail for support”.
- Ask for the comparison with the previous month, or the same month last year.
- Specify the useful split: by app, by country, by language.
Three questions to try
- “Which countries have the lowest App Store rating this quarter?”
- “Is our reply delay to negative reviews improving since the summer?”
- “Which topics come up in five-star reviews?”
Setup
- An administrator connects Google Play and App Store Connect in Data sources: the Google Play and App Store Connect guides cover the steps. For Google Play, the review reports address imports the full history.
- They open the apps to leadership, support or product.
- Each member adds Persyst to their assistant (getting started) and asks their question.
Limits to know
- Read-only: the assistant can draft replies to reviews, not publish them.
- Without the review reports address, Google Play only returns the last 7 days: comparing with the previous month needs the history.
- Reviews only: no downloads, revenue or crashes.
Questions
Frequently asked questions
Where do the numbers come from?
From Persyst’s statistics tools, which count over all imported reviews: count, average rating, star distribution, reply rate and delay. The assistant does not compute an average from the few reviews it read.
Can we follow several apps or countries?
Yes. Statistics group by app, and by country for the App Store or by language for Google Play. Each member only sees the apps open to them.
Do the ratings match the stores?
Not exactly. Google weights its rating differently, and Apple does not expose star-only ratings. For month-over-month tracking, the trends computed by Persyst remain comparable with each other.
Can we get this summary automatically?
Persyst answers questions asked from the assistant; it does not send reports on its own. Keep the question in a project or conversation of your assistant to ask it again each month.