🧠 AI Review Intelligence Engine

Pull every review from Google Maps, Yelp, Tripadvisor, Trustpilot, G2, and Capterra into one unified dataset — then get an AI-generated Voice-of-Customer report you can hand to a CEO.

Built for: brand managers • M&A diligence teams • marketing agencies • SaaS founders • investors • competitive intelligence analysts.

---

What this Actor does that no other Actor does

Single-platform scrapers	This Actor
One platform, raw reviews	Up to 6 platforms in one run, normalized to one schema
You build the analysis yourself	AI Voice-of-Customer report included (themes, churn signals, recommendations)
No competitor tracking	Specify competitor names → automatic mention detection
Static rating	Sentiment trajectory — comparing last 90 days vs. prior 9 months
All reviewers treated the same	Reviewer-type segmentation (first-timer vs. verified vs. repeat)
No churn detection	"Won't return," "switching to," "canceled" signals flagged

Inputs

Field	Required	Default	What it does
businessName	✅	—	"Acme Dental Clinic" or "HubSpot CRM"
platforms	✅	[google_maps, trustpilot]	Which review sources to hit
businessUrl	optional	—	Helps disambiguate when multiple businesses share a name
location	optional	—	E.g. "San Francisco, CA" — for local businesses
directPlatformUrls	optional	—	Skip search; jump straight to known listing URLs
maxReviewsPerPlatform	optional	500	Cap per platform
monthsLookback	optional	12	Only fetch reviews newer than N months
generateAiReport	optional	true	Toggle the AI synthesis step
geminiApiKey	conditional	—	Required if generateAiReport=true. Free at ai.google.dev
competitorMentions	optional	[]	List of competitor names to flag in reviews
language	optional	en	ISO 639-1 code, or all

Output

Each review is pushed to the dataset with this schema:

{
  "platform": "google_maps",
  "review_id": "ChdDSUhNMG9nS0VJQ0FnSURneTlY...",
  "business_name": "Acme Dental",
  "rating": 5.0,
  "max_rating": 5.0,
  "text": "Great experience. Dr. Smith is...",
  "title": null,
  "language": "en",
  "reviewer_name": "Jane D.",
  "reviewer_type": "repeat",
  "review_date": "2026-03-15T00:00:00+00:00",
  "owner_response": "Thank you Jane!",
  "owner_response_date": "2026-03-16T00:00:00+00:00",
  "sentiment": null,
  "competitor_mentions": [],
  "churn_signal": false,
  "url": "https://www.google.com/maps/place/..."
}

The Voice-of-Customer report is saved to the key-value store under two keys:

• SUMMARY — JSON summary of the run
• VOC_REPORT — Markdown executive report (preview-ready)

Pricing — Pay-per-event

You pay only for what the Actor actually delivers.

Event	Price	When charged
actor-start	$0.01	Once per run
review-scraped	$0.003	Each review extracted & normalized
platform-completed	$0.05	Each platform that returns ≥1 review
ai-analysis-generated	$0.50	When the VoC report is produced

Worked example. Run on a hotel across Google Maps + Tripadvisor + Trustpilot, retrieving 600 reviews total, with the AI report:

• Start: $0.01
• Reviews: 600 × $0.003 = $1.80
• Platforms: 3 × $0.05 = $0.15
• AI report: $0.50
• Total: ~$2.46

You set a hard spending cap per run in the Apify Console — the Actor stops gracefully when it hits it.

Why use this over the cheaper single-platform scrapers?

A single platform tells you part of the story. All six together tell you what's actually happening:

• A SaaS with great Trustpilot reviews but declining G2 ratings is losing power users — that signal only appears when you compare both.
• A restaurant with 4.5★ on Google Maps but 3.2★ on Yelp has a verified-buyer-vs-tourist problem — useful for hospitality investors doing due diligence.
• A B2B brand whose reviews mention a competitor 3× more often this quarter than last quarter is losing a category positioning battle — competitor mention tracking surfaces this.

Common use cases

• Brand monitoring — daily scheduled run, alert on churn-signal spikes
• M&A diligence — pull all reviews of an acquisition target across platforms in one click
• Competitive intel — run on a competitor with competitorMentions: ["yourBrand"]
• Voice-of-Customer for marketing — feed top complaint themes into ad-copy decisions
• Investor deal screening — quick health score on a portfolio company

Recommended for AI agents (MCP)

This Actor returns clean structured JSON; it works well as a tool inside Claude, Cursor, or any MCP client. Connect via the Apify MCP server and ask: "Give me a Voice-of-Customer report on Acme Dental across Google Maps and Trustpilot."

Tips for best results

1. Use direct URLs when you know them. Most accurate disambiguation.
2. Add location for local businesses. Especially helpful for chains.
3. Start with maxReviewsPerPlatform: 100 when testing, then scale up.
4. For SaaS, use G2 + Capterra together. Same product, different audiences.
5. Set monthsLookback: 6 for recency-sensitive analysis. The AI report's sentiment trajectory works best with a focused window.

Roadmap

• Apple App Store + Google Play scraper modules
• Trust signals: detect suspicious review velocity (potential review fraud)
• Multi-language AI synthesis (currently English-only)
• Webhook delivery on completion
• Side-by-side comparison mode (analyze 2+ businesses simultaneously)

Issues, requests, custom builds

Open an issue on the Actor's Issues tab and we'll respond within 24 hours.