Human-in-the-loop post designer with Mistral AI, ImageKit, and LinkedIn publishing
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 16 nodes and runs when a chat message arrives. Along the way it connects Mistral Cloud Chat Model, Gmail, S3 and LinkedIn.
How it runs
Trigger: When a chat message arrives.
- Edit Fields (Edit Fields (Set)): sets 1 field: post
- AI Agent: runs an AI agent, with model: Mistral Cloud Chat Model; output parser: Structured Output Parser
- Edit Fields (Edit Fields (Set)): sets 3 fields: line1, safeName, line2
- HTTP Request: calls an HTTP API
- S (S3): upload
- Merge: merges the data from its input branches
- text to html (AI Agent): runs an AI agent, with model: Mistral Cloud Chat Model
- LinkedIn: uses LinkedIn
- Send Content for Approval (Gmail): send and wait for a reply
- Approval Result (Switch): routes items into 3 branches
…plus 2 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Revision based on feedback (v1.9): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Revision based on feedback (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (11)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Edit Fields (Set)
n8n-nodes-base.set - Mistral Cloud Chat Model
@n8n/n8n-nodes-langchain.lmChatMistralCloud - Gmail
n8n-nodes-base.gmail - Switch
n8n-nodes-base.switch - AI Agent
@n8n/n8n-nodes-langchain.agent - Merge
n8n-nodes-base.merge - S3
n8n-nodes-base.s3 - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - LinkedIn
n8n-nodes-base.linkedIn - HTTP Request
n8n-nodes-base.httpRequest
From the author
📋 Description This n8n workflow streamlines AI-powered post creation with image banners, includes manual approval steps, and publishes to LinkedIn — all dynamically. It uses ImageKit.io to edit images, stores them on S3, and generates and revises posts…