The Claude Playbook to Predict Virality
How to use Claude and Meta’s TRIBE v2 to pre-test every hook, thumbnail, and video before you publish.
Meta just dropped something wild.
An open-source model that predicts how your brain reacts to content before you publish it.
The model is trained on 1,000 hours of fMRI scans from 720 real volunteers watching movies, listening to podcasts, and reading text, it predicts large-scale patterns of brain activity over time when you consume something.
A creator on X took an already-edited AI UGC video draft, ran it through the model, looked at the engagement curve, moved the highest-engagement moment to the front, cut the dead zones where the brain went flat, and reposted the new cut. The views were insane.
📚 By the end of this guide you’ll have a working TRIBE v2 + Claude system: drop in 10 hook variations and get back a ranked list with the neural score and the rewrite suggestion. The same flow runs across thumbnail mocks, ad copy paragraphs, and video drafts.
Inside you will find:
What TRIBE v2 Actually Is
The 30-Minute Setup
The 4 Claude Projects to Pre-Test Hooks, Thumbnails, Videos and Ad Copy
How to Read the Neural Map (and What to Change When Engagement Drops)
The CLAUDE.md That Ties the Whole Stack Together
👋 Just a quick note before you continue!
Building great AI systems and agents is quickly becoming one of the most important advantages a startup can have. So we’ve been building non-stop and this will become a much bigger part of PMF going forward.
From now on, as a premium subscriber, you’ll get access not just to the best resources on fundraising and growth (160+ Playbooks, 65+ Success Stories, 30+ Pitch Deck Collections, 25+ Investor Resources), but also:
🤖 3+ New AI agent Templates Every Week
📚 A Growing Library of 20+ AI Agents
Here, few examples:
We’re already 70,000+ founders and operators inside.
The rest of the article is only available to premium subscribers.
Let’s begin!
