Review Intelligence — analyze real reviews from every site

Every real review about a market — collected, themed, quantified, and distilled into a brief any LLM can reason over.

Reviews are the biggest body of honest product feedback on the internet, but they're useless in the shape they come in: scattered across Google Maps, Trustpilot, Yelp, G2 and the app stores, thousands at a time, far too long to paste into ChatGPT or Claude. This Actor fixes the shape. Point it at the companies you care about — yours, a rival's, or every player in a category — and it collects their reviews, tags the recurring themes, counts how often each one comes up per company, pulls representative quotes and switching reasons, and compresses all of it into a ~10k-token markdown brief built for LLM reasoning. One click on Copy for LLM and you're asking Claude "where is the gap nobody serves in this market?" — with the evidence attached.

Own-review monitoring is built in too: run it on a Schedule with your company ticked and each run emails you what's new, with sentiment, a rating trend, and a ready-to-edit reply draft for every fresh review.

Ask it a real question

Pick what you want to learn and the report, the analyst prompt and the AI summary reshape around it:

Category gaps — unmet needs nobody solves · What's already well served — where not to compete · What people love · Competitor weaknesses — battlecard · Why customers switch · Pricing objections · Unmet feature requests · Onboarding & setup friction · Support quality · Positioning & messaging · Own-reputation monitor — or type a custom question and it's answered over the distilled brief.

The platforms it covers

Platform	What you give it	Powered by
G2	the G2 product page URL	automation-lab/g2-scraper
Trustpilot	the domain, e.g. company.com	memo23/trustpilot-scraper-ppe
Google Maps	the listing's URL	compass/Google-Maps-Reviews-Scraper
Yelp	the Yelp business page URL	web_wanderer/yelp-reviews-scraper
Apple App Store	the app's numeric ID	thewolves/appstore-reviews-scraper
Google Play	the app's package name	thewolves/google-play-reviews-scraper

We didn't reinvent the wheel — the best review scrapers already live on the Apify Store, so we orchestrate them on your own account and do the part they don't: normalize, theme, quantify, distill. Fill in only the links each company has; up to 10 companies per run.

📍 Where else do you want reviews from?

Tripadvisor · Capterra · Amazon · Facebook · Booking.com · Software Advice · somewhere we haven't thought of? Tell us on the Issues tab — we read every request and build the most-asked-for platform next. 🙏

🧪 Early access. New and priced lean — pay only when you run, no subscription. Something missing or broken? Open an issue — we read every one. 🙏

How it works — and why 20,000 reviews cost the same as 30

The pipeline is deliberately split: we do the cheap deterministic work — collect, normalize, theme, count — and your LLM does the expensive reasoning over the distilled result.

1. Collect. Each company's reviews from every site you gave, on your own Apify account. You set the window — "reviews from the last N days" (or 0 for the entire history, once).
2. Never re-scrape. Reviews land in a persistent corpus; after the first backfill every run fetches only what's new, while the report still covers the whole window. If a burst of reviews ever exceeds the safety cap, the run says so loudly instead of silently dropping the overflow.
3. Theme. Every review is tagged with sentiment and recurring topics. The vocabulary isn't fixed: the Actor derives the themes that actually matter for your category (once, cached), then a free rules engine counts them across the entire corpus — so theming 20,000 reviews costs nothing extra.
4. Distill. Per company: rating, volume, sentiment split, top themes with % frequencies, representative quotes per theme, and switching signals — compressed into a brief that fits any LLM's context. Raw dumps never happen (8 vendors × 1,200 reviews is ~1M tokens; the brief is ~10k).
5. Deliver. A shareable dashboard with Copy for LLM (analyst prompt + brief on your clipboard) and Download full corpus (one JSONL row per review), a clean dataset, an email digest, and an AI summary of your chosen question right at the top.

Two ways to run it

• Category / competitor study — add several companies, tick nobody (or just yourself). The report compares every company against every other: ranked ratings, theme frequencies side by side, what each vendor's customers complain about. This is market research from primary sources, reproducible on demand.
• Own-review monitoring — tick "This is my company", add your email, put it on a weekly Schedule. Each run brings the new reviews, sentiment and trend, a ✍️ reply draft for every new review (personalized, skips ones you've answered), an optional per-review alert email, and an AI action plan. Quiet when nothing happened, loud when something did.

Set it up in 2 minutes

1. Add the companies — a name plus the review-site links each one has. One Google Maps or G2 URL is enough to start.
2. Pick what you want to learn (or leave the default full report) and how far back to look.
3. Connect your Apify account in the Access section — the review scrapers run on it, so the data is yours and the scraper fees are transparent.
4. Hit Start. For monitoring, use the Schedule tab — the incremental engine makes weekly runs nearly free.

Costs

One flat fee, only when you run — no subscription, no per-review or per-feature charges.

• $0.15 per GB of run memory at start — at the default 1 GB that's about $0.15 per run, everything included: fetching, theming, the brief, the dashboard, the email digest and the AI summary.
• AI analysis is included — Claude runs on our built-in key at no extra charge; bring your own Anthropic key if you prefer, and a keyless rules engine is always available as fallback.

Plus the background review scrapers' own pay-as-you-go fees, billed directly to your own Apify account (typically cents per platform). Because the engine only fetches new reviews after the first run, a scheduled check often costs almost nothing beyond the flat fee.

Ask your AI assistant (MCP)

Works as an agent tool out of the box: connect mcp.apify.com to Claude, Cursor, or any MCP client and just ask — "what do people complain about across CRM tools?" or "any new reviews for my company this week?" — and it runs this Actor with the right inputs.

Notes

Reads publicly visible reviews only and logs into nothing. The review scrapers run on your own Apify account (your token or a one-click connector — see the input's Access section); the corpus, state and dashboard live in your own Apify storage. We host nothing.

Want Tripadvisor or Capterra next? Tell us which one you need first on the Issues tab. 🙏