If you're building automations with n8n, LinkedIn content is one of the more satisfying workflows to tackle because the manual version is genuinely painful at scale, and the automated version is actually possible to get right.
This post covers the full technical architecture of a LinkedIn post automation workflow using n8n + Google Gemini + DALL·E, including the parts most write-ups skip: prompt design, error handling, approval gates, and what the workflow can't do reliably.
There's also a free downloadable JSON at the end.
The Problem This Solves
Posting consistently on LinkedIn requires repeating the same cycle every few days:
