Prompts.
Copy. Run in ChatGPT or Claude with one click. Stolen and refined from issues you should be reading.
The Agent Swarm Architect
Designs a multi-agent structure for a real task you are stuck on — with an explicit failure budget, validators kept separate from producers, and a stop rule.
The 'Is This Actually Done?' Audit
Interviews you about one piece of AI-produced work, then tells you whether it's actually done or just looks done -- built around what the Remote Labor Index found about where AI deliverables actually fail.
The Login-Wall Task Audit
Interviews you about the recurring task you keep doing yourself, then tells you honestly whether it's a good fit for a work agent that now remembers its own login — and drafts the actual handoff instructions.
The Agent Cost Audit
Answer 5 questions about your AI automations and get a personalized cost audit — what you're actually spending, whether your setup survives the billing change, and the exact optimizations that matter for your situation.
The Research Brief
Turn any question you're wrestling with into a sourced, analyst-grade research brief — it interviews you first, then runs in ChatGPT, Claude, Gemini, or any model.
The Agent Handoff Audit
Tells you the single best task to hand an AI agent first — scores it for readiness, ranks your top three, and hands back a low-risk pilot you can test-drive this week.
The Agent Fit Finder
Answer five quick questions and this prompt names the 24/7 AI agent that actually fits how you work — ChatGPT Agent, Claude Cowork, or Gemini Spark — and which to skip.
The Night-Shift Audit
A 5-question interview that finds the 3 recurring tasks in your work or life best suited to a scheduled AI agent — then hands you a step-by-step setup for the top one, matched to your tech comfort level.
