📊 Generate Brave Search Goggles with DataForSEO, Firecrawl, OpenAI and Postgres
⚡ 69 views · 📊 Market Research & Insights
💡 Pro Tip — For competitive intelligence, ScraperNode can automate the data collection — Yelp reviews, Glassdoor company data, and Crunchbase profiles all return structured JSON you can feed straight into this workflow.
Description
Who’s it for
Business owners, industry specialists, and AI developers building domain-specific search experiences. It generates custom search filters to boost technical authorities and block lead-gen aggregators, requiring no advanced SEO expertise. Pre-configured for the Dutch plastering industry, but universally adaptable.
What it does
Automates the creation of custom Brave Search Goggles to ground LLMs and AI agents in noise-free, high-authority industry content. This strict filtering ensures RAG pipelines consume pre-optimized, expert-verified data for accurate question answering and reduced hallucinations.
How it works
- Domain Intersection: Uses DataForSEO to identify high-value search terms by extracting exact keyword overlaps between top competitors.
- SERP & Mapping: Fetches the Top 100 Google results for these terms and uses Firecrawl to map the internal architecture (“Power Folders”) of the ranking domains.
- AI Auditing: An OpenAI GPT-4o agent evaluates each domain’s structure, classifying them (e.g., Manufacturer, Retailer, Aggregator) and assigning strict Goggle rules (
boost,downrank,discard) based on technical depth. - Live Deployment: Stores rules in Postgres, formats them into valid Brave Goggle syntax via a custom SQL View, and automatically syncs to a public GitHub Gist.
Requirements
- Postgres: Stores rules, audit trails, and generates the Goggle syntax.
- DataForSEO API: Extracts competitor intersections and live SERP data.
- OpenAI API: Powers the domain classification agent.
- Firecrawl API: Maps internal domain architectures.
- GitHub Account: Hosts the live Goggle file via Gists.
How to adapt the AI Auditor for other niches
To pivot this workflow to a new industry (e.g., Healthcare or Legal), update the System Prompt inside the Information Extraction Agent. Adjust the AI’s persona, redefine which domain types represent true authority (to boost), and explicitly define your industry’s specific noise (to discard).
PS
Goggles must be submitted to Brave Search before they can be used with the API. Visit search.brave.com/goggles/create to register your Goggle.
🔗 Nodes Used
HTTP Request, Postgres, Schedule Trigger, OpenAI Chat Model, Information Extractor
📥 Import
Download workflow.json and import into n8n:
Workflow menu → Import from File