Trustpilot review analysis: topic clustering and AI ins

This workflow automates the collection, semantic analysis, and interpretation of customer reviews from Trustpilot. It is designed for professionals who need to quickly turn large volumes of textual feedback into structured business insights without manual review.

## Who it´s for
- Marketers analyzing customer reviews
- E-commerce owners seeking to improve products based on feedback
- Analysts automating insight extraction from public sources
- Companies using vector databases for NLP tasks

## What the automation does
- Starts manually and clears previous data in Qdrant
- Scrapes reviews from Trustpilot for a given domain (e.g., freddiesflowers.com)
- Extracts author, rating, date, and review text
- Converts texts into vector embeddings using OpenAI
- Clusters reviews by semantic similarity via K-means algorithm
- Filters significant clusters (3+ reviews)
- Generates insights (summary, sentiment, suggestions) using GPT-4o-mini and exports to Google Sheets

## What´s included
- Ready-to-use n8n workflow
- Manual trigger and sequential processing logic
- Integrations with Trustpilot (via HTTP API), Qdrant, OpenAI, and Google Sheets
- Basic text guide for adaptation and launch

## Requirements for setup
- n8n instance with Python node support
- Access to Qdrant (local or cloud)
- OpenAI API key
- Google Sheets account with write permissions
- Basic knowledge of API configuration and environment variables

## Benefits and outcomes
- Saves time on manual analysis of hundreds of reviews
- Reveals hidden patterns of dissatisfaction (e.g., delivery, packaging)
- Automatically generates product improvement suggestions
- Centralizes insights in Google Sheets for team collaboration
- Enables regular brand reputation monitoring
- Supports data-driven decision-making

## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via Telegram: @gleb923.