Get your free personalized podcast brief

We scan new podcasts and send you the top 5 insights daily.

Bill Caskey suggests ending the AI training session by asking what other questions should be added. That prompt surfaced a missing question—why you do the work—which he had not thought to include in the original ten. It turns the tool into a collaborator on the training design itself.

Related Insights

Move beyond using AI for data consolidation and generation by treating it as a tough critic. Prompt it with questions like, "What have I missed?" or "If you were a top consultant, what would you have spotted?" This reframes the AI as a thought partner, forcing it to challenge your assumptions and uncover strategic blind spots.

Go beyond simple instruction. Explicitly prompt your AI to use tools like `ask_user_question` to push your thinking, question your goals, and suggest alternative angles. This transforms the AI from a simple executor into a powerful strategic thinking partner.

Instead of trying to craft a perfect, detailed prompt, Andrew Wilkinson tells the AI his high-level goal and instructs it to "ask me a shitload of questions to determine your prompt." The AI then conducts a 5-10 minute interview, gathering all necessary context to produce a superior result.

Treat AI not just as a tool, but as a meta-tool that can teach you to improve your own usage. Regularly asking prompts like "How could I be using you better?" or "What questions should I be asking?" can reveal new capabilities and refine your prompting skills.

Instead of spending time trying to craft the perfect prompt from scratch, provide a basic one and then ask the AI a simple follow-up: "What do you need from me to improve this prompt?" The AI will then list the specific context and details it requires, turning prompt engineering into a simple Q&A session.

Instead of providing a detailed but potentially incomplete prompt, ask the AI model to interview you about your goal. This meta-prompting technique forces clarification and helps uncover "unknown unknowns" you hadn't considered, leading to a much better final output.

Instead of just giving AI a task, command it to interview you first. By having the AI ask clarifying questions about assumptions, context, and potential gaps, you can surface your own unknown unknowns and provide the necessary context for a high-quality output.

This single sentence forces the AI to stop guessing and instead request the specific details it needs. This simple addition transforms the interaction from a command to a collaboration, dramatically improving the quality and relevance of the output by ensuring the AI has full context before acting.

Instead of manually maintaining your AI's custom instructions, end work sessions by asking it, "What did you learn about working with me?" This turns the AI into a partner in its own optimization, creating a self-improving system.

A simple meta-question like "Is there something I'm not asking you?" can unlock an AI agent's more advanced, proactive capabilities. In the podcast, this prompt revealed superior strategies like monitoring competitor sponsors and setting up automated follow-up sequences, which were more valuable than the original request.

Ask AI what training questions you forgot | RiffOn