A design thinking framework for AI, developed in partnership with Decoded Futures
Train Your AI: Download the POP-IT Coach prompt to paste into ChatGPT, Claude, or any AI assistant. It will guide you through the framework step-by-step, acting as your personal POP-IT coach to build your first Custom GPT.
What is the problem you are trying to solve?
Think about a specific bottleneck in your current workflow. Focus on something small and testable that affects a real person or team, not a vague aspiration.
What do you want to see from the AI when you're done?
Be specific about the artifact you need: a brief, CSV, creative asset, mini-app, or automation. Picture exactly what success looks like in your hands.
What instructions does the AI need to accomplish the task?
Write clear instructions as if you're briefing a smart intern. Include the role you want the AI to play, the steps to follow, and when it should ask for clarification.
What context or documentation can you share with the AI?
Gather your examples, data, links, and constraints. The more relevant context you provide, the better your AI will understand and deliver what you need.
How will you know it's working?
Define your success criteria before you build. Pick measurable outcomes like accuracy, speed, or user adoption so you'll know when you've achieved "good enough."