This article provides a complete, practical walkthrough of the Splitout Code Export Webhook n8n agent. It connects HTTP Request, Webhook across approximately 1 node(s). Expect a Intermediate setup in 15-45 minutes. One‑time purchase: €29.

What This Agent Does

This agent orchestrates a reliable automation between HTTP Request, Webhook, handling triggers, data enrichment, and delivery with guardrails for errors and rate limits.

It streamlines multi‑step processes that would otherwise require manual exports, spreadsheet cleanup, and repeated API requests. By centralizing logic in n8n, it reduces context switching, lowers error rates, and ensures consistent results across teams.

Typical outcomes include faster lead handoffs, automated notifications, accurate data synchronization, and better visibility via execution logs and optional Slack/Email alerts.

How It Works

The workflow uses standard n8n building blocks like Webhook or Schedule triggers, HTTP Request for API calls, and control nodes (IF, Merge, Set) to validate inputs, branch on conditions, and format outputs. Retries and timeouts improve resilience, while credentials keep secrets safe.

Third‑Party Integrations

• HTTP Request
• Webhook

Import and Use in n8n

1. Open n8n and create a new workflow or collection.
2. Choose Import from File or Paste JSON.
3. Paste the JSON below, then click Import.
4. Show n8n JSON

   Title:
   Automating Customer Insight Extraction from Trustpilot Reviews Using n8n, Qdrant, and OpenAI
   
   Meta Description:
   Discover how to build an automated customer insights pipeline using n8n, Trustpilot reviews, Qdrant vector store, and OpenAI. Learn to cluster reviews, extract key themes, and export actionable insights to Google Sheets.
   
   Keywords:
   n8n workflow, Qdrant, Trustpilot reviews, OpenAI GPT, AI customer insights, vector database, clustering reviews, customer feedback analysis, data automation, RAG pipeline, business intelligence automation
   
   Third-party APIs Used:
   
   1. Trustpilot (scraping public review data via HTTP).
   2. Qdrant (Vector Database API for storing and querying vectorized data).
   3. OpenAI API (text-embedding-3-small, gpt-4o-mini for embeddings and LLM-driven insights).
   4. Google Sheets API (Exporting final insights into a spreadsheet for visualization or reporting).
   
   —
   
   Article:
   
   Turning Trustpilot Reviews into Actionable Insights with n8n, OpenAI, and Qdrant
   
   In the age of data-driven decision-making, businesses need efficient ways to extract meaningful insights from sprawling volumes of customer feedback. Manually reading hundreds of reviews is not only time-consuming but also prone to oversight. That’s where automation and AI can shine. This article showcases a powerful n8n workflow that turns raw Trustpilot reviews into completely automated, sentiment-based insights—exported neatly into a Google Sheet ready for action.
   
   Built using open-source tools and AI integrations, this system consists of nine discrete steps. It scrapes reviews, branches text into manageable chunks, vectorizes semantic content, clusters similar feedback, and generates qualitative summaries using a large language model (LLM). Let’s break it down.
   
   —
   
   Step 1: Start with a Clean Slate
   
   Before importing new Trustpilot reviews, the workflow first clears any existing data from the Qdrant vector database for the specified company. This makes sure the analysis is based strictly on fresh, relevant data only—vital for comparing sentiments and topics over different time periods.
   
   —
   
   Step 2: Scrape Trustpilot for Company Reviews
   
   Using the HTTP Request and HTML Extractor nodes, the workflow scrapes the latest review pages (up to three by default) for the specified company on Trustpilot. It captures detailed metadata including:
   
   - Reviewer name and country
   - Review title and content
   - Star rating
   - Date posted
   - Date of experience
   - Review URL
   
   This data is normalized into arrays and then zipped into structured objects for processing.
   
   —
   
   Step 3: Vectorize and Store Reviews in Qdrant
   
   Each review is passed through OpenAI’s text-embedding-3-small model, producing high-dimensional vector representations that capture semantic meaning. These embeddings are stored in Qdrant, a vector database optimized for similarity searches. Through this, the system can group together reviews that “feel” alike—even if they don’t use similar words.
   
   Qdrant isn't just a place to store data: it's a core analytics engine that makes clustering and retrieval fast and intelligent.
   
   —
   
   Step 4: Trigger an Insight Subworkflow
   
   Once the reviews have been stored in Qdrant, a subworkflow is triggered to handle the analysis. This step takes company metadata along with a date window (the current month by default) to scope review data for temporal insights—this makes monitoring trends easy, such as shifts in sentiment after product updates or marketing campaigns.
   
   —
   
   Step 5: Retrieve Targeted Reviews for Analysis
   
   Using Qdrant’s Filter and Scroll API capabilities, matching reviews for the specified period and company are retrieved. The query returns both metadata and the review’s vector representation, which are then passed into the clustering phase.
   
   —
   
   Step 6: Cluster Reviews Using K-Means
   
   Leveraging Python’s scikit-learn, the vectorized reviews are grouped into a maximum of five clusters using k-means clustering. These clusters capture similar themes or pain points shared across multiple reviews.
   
   Each cluster is then filtered to ensure it has at least 3 reviews—helping to focus only on feedback that is statistically significant.
   
   —
   
   Step 7: Fetch Review Payloads Per Cluster
   
   Once clusters are identified based on shared vector proximity, corresponding review payloads are retrieved from Qdrant. This ensures that the LLM receives full-text access to all reviews in each cluster, including contextual metadata.
   
   —
   
   Step 8: Generate Qualitative Insights Using OpenAI
   
   This is where the magic happens. For each valid cluster, GPT-4o-mini is tasked with summarizing the most common themes, delivering high-level insights, and assigning a sentiment rating. For example, one group of reviews might highlight “slow delivery,” while another might praise “excellent flower arrangement.”
   
   Additionally, the model suggests improvements where necessary—turning raw feedback into strategy-ready recommendations.
   
   —
   
   Step 9: Export Results to Google Sheets
   
   Finally, the workflow formats the insights, metadata, cluster counts, and raw clustered reviews into a structured JSON object. It then appends this info to a predefined Google Sheet. Business users can open the sheet and get immediate answers to:
   
   - What customers liked
   - What frustrated them
   - What overall sentiment was
   - Suggested improvements
   
   This static snapshot allows for easy reporting, future trend comparisons, and stakeholder presentations.
   
   —
   
   Why This Workflow Matters
   
   This no-code to low-code automation is accessible even for non-developers. Featuring integrations with Qdrant, OpenAI, and Google Sheets, this n8n pipeline represents a modern “RAG” (retrieval-augmented generation) architecture boiled down to a business-friendly stack.
   
   In short, it unlocks the ability to transform unstructured customer feedback into structured, human-readable insights—with zero manual effort.
   
   —
   
   Conclusion
   
   Whether you're a startup trying to scale customer service or an established brand monitoring seasonal sentiment shifts, this n8n workflow is a game-changer. It not only automates the boring stuff (scraping, parsing, storing) but brings in state-of-the-art AI to make sense of it all.
   
   By combining Trustpilot data, vector databases, machine learning clustering, and AI summarization—this system gives every team the power to truly listen to their customers.
   
   —
   
   Want to Try It?
   
   You can replicate this setup using n8n’s visual editor, a free OpenAI key, and a running Qdrant instance. For a guided walkthrough, connect with the n8n community or join the Discord.
   
   Sample output sheet: https://docs.google.com/spreadsheets/d/e/2PACX-1vQ6ipJnXWXgr5wlUJnhioNpeYrxaIpsRYZCwN3C-fFXumkbh9TAsA_JzE0kbv7DcGAVIP7az0L46_2P/pubhtml
   
   Happy automating!

5. Set credentials for each API node (keys, OAuth) in Credentials.
6. Run a test via Execute Workflow. Inspect Run Data, then adjust parameters.
7. Enable the workflow to run on schedule, webhook, or triggers as configured.

Tips: keep secrets in credentials, add retries and timeouts on HTTP nodes, implement error notifications, and paginate large API fetches.

Validation: use IF/Code nodes to sanitize inputs and guard against empty payloads.

Why Automate This with AI Agents

AI‑assisted automations offload repetitive, error‑prone tasks to a predictable workflow. Instead of manual copy‑paste and ad‑hoc scripts, your team gets a governed pipeline with versioned state, auditability, and observable runs.

n8n’s node graph makes data flow transparent while AI‑powered enrichment (classification, extraction, summarization) boosts throughput and consistency. Teams reclaim time, reduce operational costs, and standardize best practices without sacrificing flexibility.

Compared to one‑off integrations, an AI agent is easier to extend: swap APIs, add filters, or bolt on notifications without rewriting everything. You get reliability, control, and a faster path from idea to production.

Best Practices

• Credentials: restrict scopes and rotate tokens regularly.
• Resilience: configure retries, timeouts, and backoff for API nodes.
• Data Quality: validate inputs; normalize fields early to reduce downstream branching.
• Performance: batch records and paginate for large datasets.
• Observability: add failure alerts (Email/Slack) and persistent logs for auditing.
• Security: avoid sensitive data in logs; use environment variables and n8n credentials.

FAQs

Can I swap integrations later? Yes. Replace or add nodes and re‑map fields without rebuilding the whole flow.

How do I monitor failures? Use Execution logs and add notifications on the Error Trigger path.

Does it scale? Use queues, batching, and sub‑workflows to split responsibilities and control load.

Is my data safe? Keep secrets in Credentials, restrict token scopes, and review access logs.