How to Make AI UGC TikTok Slideshows That Hit 26.4M Views a Week (GPT-6 + Postiz Workflow)

Pedro Pérez describes a repeatable AI-generated TikTok slideshow workflow that he says produced more than 26 million weekly views by adapting proven formats rather than inventing content from scratch. His process begins with identifying recently successful, repeatedly used slideshow structures in a target niche, then analyzing their hooks, pacing, emotional arcs, visuals, calls to action, comments, and music to understand the mechanisms driving engagement. He uses GPT-6 Astra to turn those patterns into distinct story concepts and GPT Image 2.5, often supplemented with Pinterest-style imagery and recurring AI avatars, to create batches of six-to-ten-slide posts for an entire week. A ChatGPT agent connected to Postiz then organizes media, captions, posting schedules, and distribution across accounts, while allowing a final human review. The approach emphasizes testing and iteration: formats exceeding roughly 10,000 to 15,000 views are adapted into variations, while those below 3,000 views are dropped, with successful posts becoming templates for future production.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.