i taught openclaw to replace my content team. now it posts tiktoks at 3am for 2¢ a slide.

Alex Djordjevic · Intermediate ·🤖 AI Agents & Automation ·2mo ago
I built an OpenClaw agent called MrTok that automatically generates TikTok slideshow concepts, creates AI images using Google Gemini, adds native Proxima Nova text overlay, and auto-drafts to TikTok via Postiz — for 2 cents per slide. This is the full architecture breakdown. 🎟️ Free Live Workshop — Build Your AI Ecom Agent Sunday, March 1st @ 5 PM EST → https://ecom.live/events/13 📌 WHAT'S COVERED This video breaks down every layer of the system: •⁠ ⁠Why AI images look like stock photos (and the first-person POV fix) •⁠ ⁠The scene library system: training your agent on real viral slideshows •⁠ ⁠Persona JSONs: how to make content that actually resonates with your audience •⁠ ⁠The text overlay stack that looks native on TikTok (not Canva) •⁠ ⁠How Postiz closes the loop for fully automated posting ⏱️ TIMESTAMPS 0:00 — Intro: what MrTok is and why I built it 1:12 — The output: full slideshow the agent made (unprompted) 2:44 — Starting point: Larry skill + why I upgraded to Gemini 3:57 — Architecture: the full pipeline explained 5:03 — Training data: why untrained AI looks like stock photos 6:24 — Scene library: JSON breakdown of viral slideshow shots 9:19 — Pinterest hack: drag image → instant JSON prompt template 11:37 — Persona JSON: Dog Mom breakdown 13:54 — Prompt engineering: good vs. bad (the invisible photographer problem) 16:35 — Text overlay: Proxima Nova, node-canvas, Apple emoji support 20:50 — Dashboard walkthrough: personas, formats, concepts 22:51 — Full tech stack (Next.js, Supabase, Gemini, Postiz) 23:49 — Auto-posting to TikTok with Postiz 24:44 — What's next + free workshop CTA Architecture Doc: https://abounding-star-ccb.notion.site/MrTok-Automated-TikTok-Slideshow-System-Journey-Architecture-31183a9164f681dabc76cb1c7b0a5442?pvs=73 Larry Skill (original inspiration): https://clawhub.ai/OllieWazza/larry OpenClaw: https://openclaw.ai Tags: #TikTokAutomation #AIEcommerce #OpenClaw #TikTokForBusiness #EcommerceMarketing #AIContentCreation #
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

The Context Layer: Why Enterprise AI Agents Fail Without It — and What It Actually Takes to Fix That
Enterprise AI agents often fail due to lack of context, but understanding the four-layer context problem can help fix this issue
Dev.to · Swapnil Chougule
Comparing 6 AI Routers Is a Mistake — Until You Define ‘Survived’
Evaluating AI routers requires a clear definition of success criteria, as comparing them without context is misleading
Medium · AI
Comparing 6 AI Routers Is a Mistake — Until You Define ‘Survived’
Evaluating AI routers requires defining survival metrics, as a simple comparison of 6 AI routers can be misleading
Medium · Programming
What if an AI continued thinking even after you closed the chat?
Explore the concept of AI systems that continue thinking after a conversation ends and its implications
Dev.to · Stell

Chapters (14)

Intro: what MrTok is and why I built it
1:12 The output: full slideshow the agent made (unprompted)
2:44 Starting point: Larry skill + why I upgraded to Gemini
3:57 Architecture: the full pipeline explained
5:03 Training data: why untrained AI looks like stock photos
6:24 Scene library: JSON breakdown of viral slideshow shots
9:19 Pinterest hack: drag image → instant JSON prompt template
11:37 Persona JSON: Dog Mom breakdown
13:54 Prompt engineering: good vs. bad (the invisible photographer problem)
16:35 Text overlay: Proxima Nova, node-canvas, Apple emoji support
20:50 Dashboard walkthrough: personas, formats, concepts
22:51 Full tech stack (Next.js, Supabase, Gemini, Postiz)
23:49 Auto-posting to TikTok with Postiz
24:44 What's next + free workshop CTA
Up next
Combine Skills and MCP to Close the Context Gap — Pedro Rodrigues, Supabase
AI Engineer
Watch →