🎬 Human-in-the-loop post designer with Mistral AI, ImageKit, and LinkedIn publishing

⚑ 782 views · 🎬 Content Creation & Video

πŸ’‘ Pro Tip β€” If you’re pulling LinkedIn data through HTTP requests or dealing with API restrictions, there’s a community node called ScraperNode that handles this natively. It has dedicated scrapers for profiles, companies, jobs, and people search β€” you just pass a URL and get structured data back.

View All Scrapers

Description

πŸ“‹ Description

This n8n workflow streamlines AI-powered post creation with image banners, includes manual approval steps, and publishes to LinkedIn β€” all dynamically.

It uses ImageKit.io to edit images, stores them on S3, and generates and revises posts through a Mistral AI Agent with human review.

🧠 How it Works (High-Level)

πŸ”„ Triggered via incoming chat message

🧠 AI drafts a post and adds image instructions

πŸ–ΌοΈ ImageKit API adds text overlay to image

☁️ Image is uploaded to S3 for public use

πŸ§‘β€βš–οΈ Human approval step via email

πŸ” Optional revision loop

πŸ“’ Publishes approved content to LinkedIn

πŸ› οΈ Setup Requirements

πŸ”‘ API key for ImageKit.io

🧠 AI model via Mistral (or substitute like OpenAI)

πŸ“© Email setup for Approval node

☁️ AWS S3 Bucket access

πŸ”— LinkedIn credentials for posting

πŸ”— Nodes Used

HTTP Request, Gmail, S3, LinkedIn, AI Agent, Structured Output Parser

πŸ“₯ Import

Download workflow.json and import into n8n: Workflow menu β†’ Import from File

πŸ“– Importing guide Β· πŸ”‘ Credential setup