# AI Review Intelligence — 6-Platform Scraper + VoC Reports (`sunny_spade/review-intelligence-engine`) Actor Unified multi-platform review scraping with AI-powered Voice-of-Customer synthesis. Pulls reviews from up to 6 platforms, normalizes them into one schema, then uses Gemini to extract themes, sentiment trends, churn signals, and competitive mentions. - **URL**: https://apify.com/sunny\_spade/review-intelligence-engine.md - **Developed by:** [NoCanDo](https://apify.com/sunny_spade) (community) - **Categories:** AI, Lead generation, Automation - **Stats:** 1 total users, 0 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $3.00 / 1,000 reviews This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## 🧠 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](https://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: ```json { "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. # Actor input Schema ## `businessName` (type: `string`): The business or product to analyze. Be specific — 'Acme Dental' is better than 'Acme'. For SaaS products, use the product name (e.g., 'HubSpot CRM'). ## `platforms` (type: `array`): Which platforms to pull reviews from. Each platform you check costs $0.05 when reviews are successfully retrieved. Use only the ones relevant to your business type. ## `businessUrl` (type: `string`): If two businesses share a name, providing the website helps the Actor pick the right one. Skip this if you already give a direct platform URL below. ## `location` (type: `string`): City and country/state, used to disambiguate Google Maps and Yelp matches. Ignored for SaaS platforms (G2, Capterra). ## `directPlatformUrls` (type: `object`): If you already know the exact URL of the business listing on a platform, paste it here to skip the search step. Keys must match the platform names you selected above. ## `maxReviewsPerPlatform` (type: `integer`): Caps the per-platform scrape. 500 is enough for solid AI analysis on most businesses. Set lower for cost-sensitive runs. ## `monthsLookback` (type: `integer`): Only fetch reviews from the last N months. Reduces cost and focuses on relevant signals. Set to 0 for all-time. ## `generateAiReport` (type: `boolean`): Adds an executive-summary report with themes, sentiment trajectory, churn signals, and recommendations. Charged at $0.50 per report. ## `geminiApiKey` (type: `string`): Required if 'Generate AI Report' is enabled. Free tier (1500 requests/day) is sufficient for ~50 reports per day. We never store this — it's used only during the run. ## `competitorMentions` (type: `array`): Reviewers often mention competitors ('we switched from X', 'better than Y'). Add competitor names here and we'll flag those reviews and count mentions. ## `language` (type: `string`): ISO 639-1 code. 'en' fetches English reviews only. Use 'all' to keep every language. ## `proxyConfiguration` (type: `object`): We strongly recommend Apify Proxy with residential IPs for Google Maps, Yelp, and Tripadvisor — these have aggressive anti-bot. The default is good for most cases. ## Actor input object example ```json { "businessName": "Acme Dental Clinic", "platforms": [ "trustpilot" ], "businessUrl": "https://acmedental.com", "location": "San Francisco, CA, USA", "directPlatformUrls": { "google_maps": "https://www.google.com/maps/place/...", "trustpilot": "https://www.trustpilot.com/review/example.com" }, "maxReviewsPerPlatform": 30, "monthsLookback": 6, "generateAiReport": false, "competitorMentions": [], "language": "en", "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } ``` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "businessName": "Blue Bottle Coffee", "businessUrl": "https://bluebottlecoffee.com", "location": "San Francisco, CA, USA" }; // Run the Actor and wait for it to finish const run = await client.actor("sunny_spade/review-intelligence-engine").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "businessName": "Blue Bottle Coffee", "businessUrl": "https://bluebottlecoffee.com", "location": "San Francisco, CA, USA", } # Run the Actor and wait for it to finish run = client.actor("sunny_spade/review-intelligence-engine").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "businessName": "Blue Bottle Coffee", "businessUrl": "https://bluebottlecoffee.com", "location": "San Francisco, CA, USA" }' | apify call sunny_spade/review-intelligence-engine --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=sunny_spade/review-intelligence-engine", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "AI Review Intelligence — 6-Platform Scraper + VoC Reports", "description": "Unified multi-platform review scraping with AI-powered Voice-of-Customer synthesis. Pulls reviews from up to 6 platforms, normalizes them into one schema, then uses Gemini to extract themes, sentiment trends, churn signals, and competitive mentions.", "version": "0.1", "x-build-id": "1lGJK7Ok3HnbPNrSA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sunny_spade~review-intelligence-engine/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sunny_spade-review-intelligence-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sunny_spade~review-intelligence-engine/runs": { "post": { "operationId": "runs-sync-sunny_spade-review-intelligence-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sunny_spade~review-intelligence-engine/run-sync": { "post": { "operationId": "run-sync-sunny_spade-review-intelligence-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "businessName", "platforms" ], "properties": { "businessName": { "title": "Business or Product Name", "type": "string", "description": "The business or product to analyze. Be specific — 'Acme Dental' is better than 'Acme'. For SaaS products, use the product name (e.g., 'HubSpot CRM')." }, "platforms": { "title": "Platforms to Scrape", "minItems": 1, "uniqueItems": true, "type": "array", "description": "Which platforms to pull reviews from. Each platform you check costs $0.05 when reviews are successfully retrieved. Use only the ones relevant to your business type.", "items": { "type": "string", "enum": [ "google_maps", "yelp", "tripadvisor", "trustpilot", "g2", "capterra" ], "enumTitles": [ "Google Maps (local businesses)", "Yelp (US local businesses, restaurants)", "Tripadvisor (hotels, restaurants, attractions)", "Trustpilot (e-commerce, online services)", "G2 (B2B SaaS)", "Capterra (B2B SaaS)" ] }, "default": [ "trustpilot" ] }, "businessUrl": { "title": "Business Website URL (optional, helps disambiguation)", "type": "string", "description": "If two businesses share a name, providing the website helps the Actor pick the right one. Skip this if you already give a direct platform URL below." }, "location": { "title": "Business Location (optional, for local businesses)", "type": "string", "description": "City and country/state, used to disambiguate Google Maps and Yelp matches. Ignored for SaaS platforms (G2, Capterra)." }, "directPlatformUrls": { "title": "Direct Platform URLs (advanced, optional)", "type": "object", "description": "If you already know the exact URL of the business listing on a platform, paste it here to skip the search step. Keys must match the platform names you selected above." }, "maxReviewsPerPlatform": { "title": "Maximum Reviews per Platform", "minimum": 10, "maximum": 5000, "type": "integer", "description": "Caps the per-platform scrape. 500 is enough for solid AI analysis on most businesses. Set lower for cost-sensitive runs.", "default": 30 }, "monthsLookback": { "title": "Months of History to Fetch", "minimum": 0, "maximum": 120, "type": "integer", "description": "Only fetch reviews from the last N months. Reduces cost and focuses on relevant signals. Set to 0 for all-time.", "default": 6 }, "generateAiReport": { "title": "Generate AI Voice-of-Customer Report", "type": "boolean", "description": "Adds an executive-summary report with themes, sentiment trajectory, churn signals, and recommendations. Charged at $0.50 per report.", "default": false }, "geminiApiKey": { "title": "Gemini API Key (free, get one at ai.google.dev)", "type": "string", "description": "Required if 'Generate AI Report' is enabled. Free tier (1500 requests/day) is sufficient for ~50 reports per day. We never store this — it's used only during the run." }, "competitorMentions": { "title": "Competitor Names to Track", "uniqueItems": true, "type": "array", "description": "Reviewers often mention competitors ('we switched from X', 'better than Y'). Add competitor names here and we'll flag those reviews and count mentions.", "default": [], "items": { "type": "string" } }, "language": { "title": "Review Language Filter", "type": "string", "description": "ISO 639-1 code. 'en' fetches English reviews only. Use 'all' to keep every language.", "default": "en" }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "We strongly recommend Apify Proxy with residential IPs for Google Maps, Yelp, and Tripadvisor — these have aggressive anti-bot. The default is good for most cases.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```