Prompts.
Copy. Run in ChatGPT or Claude with one click. Stolen and refined from issues you should be reading.
The Model Tier Routing Audit
Most workflows were built when one model tier was the only sane default. This prompt interviews you about one workflow you already run, step by step, then tells you which tier each step actually needs, where downgrading would be a mistake, and the single change that saves the most for the least risk.
The Jagged Frontier Audit
Tell it your job and your weekly tasks, and it hands back a personalized map: what to delegate to AI now, what to test with a safety net, and what to keep human.
The AI Adoption Audit
Turn the AI-adoption wave into your own 90-day plan. This prompt interviews you about your role, then names the three workflows to automate first, the right tool for each, and a one-paragraph pitch to get your team on board.
The AI Leverage Audit
Answer five quick questions and get the single highest-leverage task to hand to AI this week — plus a ready-to-paste prompt built for your exact job.
Design your AI verification protocol
Personal AI verification protocol designed in 5 questions, calibrated to your work, audience, and worst-case scenario.
Spec your first vibe-coded internal tool
Designs the smallest useful version of your first vibe-coded internal tool, picks Lovable, Replit, or Claude Code for your case, and gives you the opening prompt to paste.
The Two-Model Gut Check
An interview-first prompt that pressure-tests any AI answer the way an editor pressure-tests a draft — then hands you a map of exactly where two models disagree and which one to trust.
