This content originally appeared on DEV Community and was authored by prasanna-lakshmi18
This is a submission for the AI Agents Challenge powered by n8n and Bright Data
What I Built
I built an AI Agent using n8n and Bright Data that analyzes YouTube comments and generates personalized video suggestions and insights.
The goal is to help content creators or marketers understand audience sentiment, find new content opportunities, and improve engagement strategies.
Demo
n8n Workflow
I’ve shared the full workflow JSON on GitHub:
View Workflow on GitHub
Technical Implementation
Here’s how the workflow works step by step:
- Trigger → A Schedule Trigger node runs once every week.
-
Bright Data Scraper (1st Node) → Initiates a scrape of YouTube video comments, generating a
snapshotId. -
Bright Data Scraper (2nd Node) → Uses the
snapshotIdto download the comments data. - JavaScript Code Node → Parses and cleans the JSON comment data.
-
Gemini AI Node → Takes the extracted comments and generates:
- Engagement strategies
- Content improvement tips
- Email Node → Sends the processed results to the intended recipient automatically.
Bright Data Verified Node
I used Bright Data’s Verified Node to scrape YouTube comment sections efficiently and reliably. It provides structured JSON data (via snapshotId), which I could easily process inside n8n for further AI analysis.
Journey
This project taught me how to integrate:
- Bright Data scraping → for reliable comment extraction
- n8n workflow automation → to orchestrate the entire process
- Gemini AI → to provide actionable insights
- Email automation → for timely delivery of results
Challenges I overcame:
- Parsing large YouTube comment datasets in n8n
- Handling async data retrieval with Bright Data’s snapshot mechanism
- Formatting the AI-generated output in a useful way for creators
I learned how powerful combining data scraping + automation + AI can be in real-world scenarios.
This content originally appeared on DEV Community and was authored by prasanna-lakshmi18