# Review Insights

> A free, open-source Google Play review analyzer for product managers and UX designers: ranked decisions, journey maps and research reports, with the real reviews behind every point.

Turn Google Play reviews into design and product decisions

- **Problem:** App reviews are the largest free source of user feedback most teams have, and the least used. Reading thousands of them takes days, and a sentiment dashboard says how people feel, not what to change.
- **The tool:** A free, open-source app that reads every review, tags it, computes how much each problem matters, and writes decisions that cite the reviews behind them.
- **What you get:** What to fix first, where the journey breaks and a research report, with the users' own words as evidence. It also plugs into Claude, ChatGPT, Cursor and other AI apps.

- Outcome: **200 → 7** reviews to cited decisions
- Kind: Open-source tool
- Made: Jan 2025
- Tags: UX research, AI analysis, product decisions
- Source: https://github.com/ux-biswarup/google-play-scrapper-for-designers

*Chapter 01 · Why I made it*## Reviews are the feedback nobody readsApp reviews are the largest free source of user feedback most teams have, and the least used.Reading thousands of them takes days. A sentiment dashboard can say that 40% of the reviews are negative, but not what to change on Monday.So I built a tool that reads every review, works out how much each problem matters, and hands back decisions you can defend.Review Insights is for product designers, UX researchers and product managers
who want to go from reviews to decisions they can defend in a design critique
or a roadmap meeting: problems ranked by how much they matter, the moments in
the journey where people give up, and the users' own words as evidence. Every
number links back to the reviews it came from, and every claim quotes the
users.*Chapter 02 · How it decides*## Three layers you can checkMost AI review tools ask a model to summarise the reviews, and you get
confident text you can't check. Review Insights splits the work into three
layers, so you can trust the result:1) **Evidence.** An AI model tags every review: what kind of feedback it is (a
   bug, a request, friction, a complaint or praise), its themes, the step of the
   journey it is about, the emotion, how severe it is, who wrote it (new,
   long-time or paying), whether they are leaving, and anything about
   accessibility. Risky tags are double-checked: "they're leaving" and a
   competitor's name are only kept when the review says so in its own words.
2) **Analysis, computed in code.** Counts, shares, trends and scores are
   calculated, never written by the model. Impact is reach × negativity ×
   momentum; priority is impact × confidence ÷ effort. Labels like better or
   worse come from the numbers.
3) **Decisions, written by AI and checked.** The model explains and recommends,
   citing the reviews it used. Any citation to a review that doesn't exist is
   removed, so every claim points to real feedback.![The priority matrix for Pokémon GO: themes plotted by share of reviews against share of negative reviews, with login issues and account management in the act-first corner](https://www.biswarupmondal.com/playground/review-insights/problems.png)*Chapter 03 · Start in seconds*## Pick an app, and what you want to learn![Review Insights' Analyze an app screen: a search field for an app name or Play Store link, recent apps, and past analyses in the sidebar](https://www.biswarupmondal.com/playground/review-insights/new-analysis.png)An analysis starts from a goal rather than a long form:* **Health check:** what do users love and hate right now?
* **What's broken:** what made people angry this month?
* **Recent changes:** how did the last few weeks go?
* **Deep dive:** everything from the last quarter, for research.The market, the language and the number of reviews have sensible defaults you
can change: up to 2,000 reviews, any period, a rating filter, and insights in a
different language from the reviews if you need them. It shows the estimated
time and tokens before it starts.*Chapter 04 · What you get back*## Fifteen views, one set of reviewsEvery analysis opens in fifteen views, grouped by what they are for:* **Decide:** decisions ranked now, next and later, a research report you can
  download as Markdown or PDF, and your pinned quotes.
* **Understand:** an overview, problems and priorities, bugs, requests and
  complaints, a journey map, emotions, segments, risks, accessibility,
  developer replies and personas.
* **Track:** trends, one-star spikes, and what changed before and after a
  release.
* **Evidence:** every review, filterable by rating, theme, type, journey stage,
  emotion, version or text.![The journey map: an emotional curve of average rating across install, account, core experience, payments, settings, support and updates](https://www.biswarupmondal.com/playground/review-insights/journey.png)For a product designer or a UX researcher, that means usability problems
ranked by impact rather than by how loud they are, each with quotes for the
next critique; How Might We questions, likely root causes and draft
proto-personas, marked as hypotheses; and the accessibility barriers users
report, grouped by need, each with the WCAG check to run.For a product manager, it means a prioritised decision list with a metric to
watch and a status to track, what got better or worse in the last release,
early warnings when people say they're leaving, and output ready for
stakeholders.![Developer replies for Pokémon GO: reply rates by rating, the share of copy-paste replies, and the complaints left unanswered](https://www.biswarupmondal.com/playground/review-insights/replies.png)*Chapter 05 · The research assistant*## Ask it, and it looks things upThe assistant, **Ask AI**, sits beside every analysis. It works from your data,
not from memory: to answer, it reads the problem board, the journey map,
segments, trends and risks, and searches the reviews, and you can watch each
lookup as it happens. Numbers come from those lookups, and every claim is
cited: press a citation to read the review it came from.![Ask AI open beside a Pokémon GO analysis: a question about which journey stage loses the most users, the lookup it made, its cited answer and the review behind it](https://www.biswarupmondal.com/playground/review-insights/assistant.png)Each analysis gets up to five starter questions, written from what it found
and tagged with why they're there:| Tag         | Example, for Pokémon GO                                            |
| ----------- | ------------------------------------------------------------------ |
| Top problem | Why are users unhappy about login issues?                          |
| Rising      | What's behind the recent rise in account management complaints?    |
| Churn risk  | Why do 17 reviewers say they're leaving, and what would keep them? |
| Journey     | Where do users get stuck with the core experience?                 |
| Release     | Did version 0.435.1 make things better or worse?                   |A typical decision goes like this:1) Ask a starter question: "Why are users unhappy about login issues?"
2) Read the cited reviews, and pin the ones that make the case.
3) Narrow it down: "Is this worse for paying users?"
4) Turn it into options: "What are three ways to fix this, cheapest first?"
5) Check the ranked decisions, set their status, and share the research
   report, with your pinned quotes in it.Chats open as tabs, so several threads can run at once, and each analysis keeps
its own history, so the context of one app never mixes with another's.*Chapter 06 · Benchmark*## Next to the competition![Pokémon GO benchmarked against Monster Hunter Now: reviews analysed, average rating, negative and positive shares, and where Pokémon GO leads and lags](https://www.biswarupmondal.com/playground/review-insights/benchmark.png)Benchmark puts two to four analyses side by side: your app against
competitors, two markets, or two periods. The AI groups each app's themes into
shared topics; the leads, lags and lessons are computed from the reviews, each
with a quote from both sides.*Chapter 07 · Use it from your AI app*## Claude, ChatGPT, Cursor and more, through MCPReview Insights includes an MCP server. MCP, the Model Context Protocol, is
the standard way for an AI app to use another tool's data. Connected, the AI
app you already pay for can read your analyses and answer with numbers and
real quotes, using your own subscription. It can only read: it can't start an
analysis or change anything.![The Use in Claude, ChatGPT page: tabs for Claude Desktop, Claude Code, Cursor, VS Code, Codex and ChatGPT or claude.ai, the setup for Cursor, and the tools the connected app can use](https://www.biswarupmondal.com/playground/review-insights/mcp.png)The easiest way in is that page, in the app's sidebar. The setup, by app:* **Claude Desktop:** add the server to `claude_desktop_config.json` (Settings,
  Developer, Edit config) and restart. Claude starts it itself, so Review
  Insights doesn't need to be open.
* **Claude Code:** one command, below. **Codex CLI:** the same, in
  `~/.codex/config.toml`.
* **Cursor and VS Code:** point them at the running app's address,
  `http://localhost:8000/mcp/`, and keep Review Insights running.
* **ChatGPT or claude.ai in the browser:** web apps can only reach the public
  internet, so expose the app through a tunnel (Cloudflare Tunnel or ngrok),
  allow that address, and add it as a custom connector. Stop the tunnel when
  you're done: anyone with its address can read your analyses.```bash
claude mcp add review-insights --scope user \
  --env PYTHONPATH="/path/to/google-play-scrapper-for-designers" \
  -- "/path/to/google-play-scrapper-for-designers/.venv/bin/python" -m backend.mcp_server
```Connected, the AI app can list your analyses; read the overview, problems,
journey map, segments, trends, risks, accessibility and developer replies;
search the reviews for quotes; compute metrics; and compare analyses side by
side. Things to ask it:* "What are the biggest problems in my latest Pokémon GO analysis?"
* "Compare my app with the competitor analyses and list where we lag."
* "Write three Jira tickets for the top problems, with quotes as evidence."*Chapter 08 · Use it yourself*## Free, and on your own computerAnybody can run it. It's free, MIT-licensed, and the code and the full guide
are on GitHub.
You need Python 3.11 or newer, Node.js 24, and an AI model: an API key, a
ChatGPT Plus or Pro sign-in, an OpenRouter account, or a local model in Ollama.```bash
git clone https://github.com/ux-biswarup/google-play-scrapper-for-designers.git
cd google-play-scrapper-for-designers
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cd web && npm install && npm run build && cd ..
uvicorn backend.main:app --port 8000
```Then open `http://127.0.0.1:8000`:1) **Connect an AI model** from the bottom of the sidebar: paste a key
   (Anthropic, OpenAI, Gemini, OpenRouter, Groq, Mistral or any
   OpenAI-compatible server), continue with ChatGPT, connect OpenRouter, or
   point it at Ollama.
2) **Analyze an app:** New analysis, find the app, pick a goal, start.
3) **Explore and ask:** browse the views, and open Ask AI.## Your reviews and keys stay yours* **It runs locally.** Reviews and results stay on your computer. Reviews are
  sent only to the AI provider you choose, and with Ollama, nowhere at all.
* **Keys never live in the browser.** The ones you paste are encrypted on disk,
  and the encryption key is kept in your system's keychain. The app only shows
  a masked hint.
* **Other websites can't use them.** The server answers only on your own
  machine, and refuses changes requested by other websites.
* **The MCP server is local too,** unless you choose to open it through a
  tunnel.*Chapter 09 · The decisions behind it*## Why it works the way it does**The AI writes; the numbers are computed.** A number a model writes cannot be
checked. A number computed from tagged reviews links back to the reviews it
came from, so it can be defended in a critique.**Every claim quotes the users.** A finding with a review under it is evidence;
a finding without one is an opinion. The model is told never to invent numbers,
themes or quotes, and the code drops any citation that does not point at a
real review.**Any model, with your own key.** It works with Anthropic, OpenAI, Google
Gemini, OpenRouter, Groq, Mistral, a ChatGPT plan, any OpenAI-compatible
server, or Ollama on your own machine, where no review leaves it. Keys stay
out of the browser and encrypted on your computer.**Free and open source.** It is MIT-licensed and runs on your own computer, so
anyone can use it, check how it reaches a number, or change it.- **Evidence** every review tagged, risky tags double-checked
- **Analysis** every number computed in code, never written by the model
- **Decisions** written by the AI, and every citation checked> Sentiment tells you how people feel. Review Insights tells you what to do about it.

[All of the playground](https://www.biswarupmondal.com/playground)

---

- Web page: https://www.biswarupmondal.com/playground/review-insights
- Every page as markdown: https://www.biswarupmondal.com/llms.txt · full text: https://www.biswarupmondal.com/llms-full.txt
- MCP server: https://www.biswarupmondal.com/mcp
- Contact: ux.biswarup@gmail.com