Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / Reports, Analytics & Dashboards

Reports, Analytics & Dashboards

Track Weekly NPS Scores from Scraped Survey Reviews

Every week, an OpenAI agent scrapes survey reviews through Bright Data MCP, calculates the Net Promoter Score and logs it in Google Sheets.

What it does

# 📊 Track Satisfaction Scores Workflow ### ✨ *Automatically scrape survey reviews, calculate Net Promoter Score (NPS), and log results to Google Sheets for leadership insights.* --- ## 🔶 Section 1: Set the Target Survey Page ### 🧩 Nodes: * ⏰ Run Weekly NPS Tracker *(Schedule Trigger)* * ✏️ Set Survey Page URL *(Edit Fields)* ### 📝 What This Does: This section controls when and where to begin. * The Schedule Trigger node is set to run automatically — for example, every Monday at 10 AM — to check the latest customer satisfaction reviews from a specific website like Trustpilot. * The Edit Fields node allows you to define or update the target survey/review page URL (e.g., Shopify’s Trustpilot page). You can also set any other optional config like number of reviews, date range, etc. ### 🧠 Why It Matters: * Allows automation instead of manual monitoring. * Keeps your system flexible — you can easily change the source URL without editing the rest of the workflow. --- ## 🤖 Section 2: Scrape Reviews Using AI Agent ### 🧩 Nodes: * 🧠 Scrape Reviews with Agent (MCP) *(AI Agent)* * 🔌 🎯 Prompt & Guide Agent *(OpenAI Chat Model)* * 🌐 Execute Web Scrape (Bright Data) *(MCP Client)* * 📦 Parse Agent Response *(Structured Output Parser)* ### 📝 What This Does: This is where the magic happens — using AI + Bright Data to fetch live reviews. * The AI Agent launches a headless browser via Bright Data's Mobile Carrier Proxy (MCP), mimicking a real user to visit the review site. * It’s guided by an OpenAI model that understands natural prompts, like: *“Extract customer ratings, comments, and dates from Trustpilot”.* * After scraping, the Structured Output Parser turns unstructured HTML into clean JSON data — a list of reviews like: json { "rating": 2, "comment": "..." } ### 🧠 Why It Matters: * Many review sites use JavaScript — Bright Data MCP bypasses anti-bot detection. * No need to write complex scraping code — just describe what you want in plain English. * This is your data foundation — reliable, structured, fresh. --- ## 📈 Section 3: Analyze & Log NPS Results ### 🧩 Nodes: * 📊 Calculate NPS from Ratings *(Code Function)* * 📄 Log NPS to Google Sheet *(Google Sheets)* ### 📝 What This Does: This is your data analysis and reporting layer. * The Function node receives the scraped review data, calculates Net Promoter Score (NPS) by: * Mapping 1–5 sta

The steps

  1. ⏰ Run Weekly NPS Tracker
  2. ✏️ Set Survey Page URL
  3. 🧠 Scrape Reviews with Agent (MCP)
  4. 📊 Calculate NPS from Ratings
  5. 📄 Log NPS to Google Sheet
  6. 🎯 Prompt & Guide Agent
  7. 🌐 Execute Web Scrape (Bright Data)
  8. Auto-fixing Output Parser
  9. OpenAI Chat Model
  10. Structured Output Parser

Similar automations