# Generate fact-checked LinkedIn posts with Groq, Gemini, Pinecone, and Slack

> Quick overview This workflow selects and drafts a LinkedIn post from Supabase-sourced topics or newly uploaded Google Drive files, extracts and cleans source content (PDF/image/URL/text), uses Groq and Google Gemini models plus Pinecone reference patterns to generate and quality-check the draft, and publishes to LinkedIn after Slack approval. How it works 1. Runs daily on a schedule or triggers when a new file is created in a specific Google Drive folder. 2. On scheduled runs, reads eligible topics from a Supabase view and uses a Groq-powered AI agent to select a topic (or recommend skipping) before fetching the full topic record from Supabase. 3. Routes the selected topic’s source by type and extracts content by downloading and OCR-cleaning images, extracting PDF text, fetching and cleaning URL HTML, or passing through provided text into a single normalized text field. 4. Truncates the text and uses a Groq-powered AI agent to extract structured facts, angles, technical details, and pr

- **Domain**: `n8n-workflow-19735.n8n.io`
- **Provider**: n8n.io (https://n8n.io)
- **Kind**: workflow
- **Live-responds (last probe)**: None
- **Signed card**: False
- **Streaming**: False
- **Quality score**: 40%

## URLs
- Agent card: https://n8n.io/workflows/19735
- Page (HTML): https://agenstry.com/agents/n8n-workflow-19735.n8n.io
- Documentation: https://n8n.io/workflows/19735