@meta
  v: 1
  route: /lesson-3/
  generated: 2026-10-24T10:19:12Z
  ttl: 1d

@intent
  purpose: Lesson 3 teaches: Think out loud with AI
  audience: visitor, business-owner, ai-agent
  capability: learn, practice, bookmark, take-notes

@state
  lesson: 3
  title: Think out loud with AI
  key_idea: Thinking mode and doing mode are different. Say which one you're in.
  core_moves[5]{move,how,example_prompt}:
    Say you're exploring,Tell it up front you don't want a final answer yet. Otherwise it rushes to one.,We're brainstorming. Don't give me a final answer yet. Help me figure out what I'm really asking.
    "Ask for range, not one answer",One idea is a suggestion. Five different ones is a map.,"Give me five very different angles on this, including one that sounds wrong at first."
    Let it interview you,Questions pull out the things you know but didn't think to say.,"Interview me about this. One question at a time, and wait for my answer."
    Name the spark when it shows up,"When something clicks, say so and push on it. That's where the real idea is hiding.",That second idea. Why does it feel right to me? Push on it.
    Close the loop,"End every brainstorm with a written summary, or it evaporates.","Summarize what we decided, what we rejected and why, and the one next step."
  why_it_works[3]{reason,explanation}:
    It stops the rush to an answer,"Ask a question and you get an answer, even when the question was the wrong one. Saying you're exploring buys room to find the right one."
    Reacting is easier than describing,You can't always say what you want. You can almost always say what's wrong with what's in front of you. Brainstorming puts things in front of you.
    The summary turns talk into work,A good conversation that isn't written down is gone by tomorrow. The closing summary is what you hand over to the doing mode.
  common_mistakes[4]{mistake,fix}:
    Asking for the answer in the first message,Say you're exploring. Ask it to help find the question first.
    Taking the first idea,"Ask for range, then react. The first idea is rarely the best one."
    Brainstorming forever,"Set an end: \"Ten more minutes, then summarize and give me one next step.\""
    Losing the conversation,"Save the summary somewhere you'll see it: a note, a project, a task."
  exercise: "Pick a decision you've been putting off. Write the first message that sets up a brainstorm, not a request for an answer. Write yours first, then compare."
  exercise_model_answer: "We're brainstorming, no final answers. I've been going back and forth on hiring a second technician. I'm not sure if the problem is too much work, or the wrong kind of work. Ask me questions one at a time to figure out which it is. After about ten questions, tell me what you think the real question is."
  further_reading[3]{title,url}:
    Let Claude think (Anthropic),https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/chain-of-thought
    One Useful Thing (Ethan Mollick),https://www.oneusefulthing.org/
    Prompting strategies (Google Gemini),https://ai.google.dev/gemini-api/docs/prompting-strategies
  what_jason_did: "This site started that way. My business partner asked how to catch up on how I work with AI, and I didn't have an answer. I didn't ask an AI to write a course. I talked it through, first with one AI and then another. I rejected a lot: a design that looked like every other AI site, a headline that was too narrow. The spark came when one of them said people don't want a genie, they want the moment something clicks. That line became the site."
  try_today[5]:
    - Pick something you've been going back and forth on.
    - "Tell the AI you're exploring, not asking for an answer."
    - "Ask it to interview you, one question at a time."
    - "When something clicks, say so and push on it."
    - End with a written summary and one next step.
  storage: browser-only

@actions
  - id: open_practice_lab
    method: GET
    href: /lesson-3/#lab
  - id: back_to_field_guide
    method: GET
    href: /#guide

@context
  > Some of the best work starts before you know what you're asking. Brainstorming with AI isn't about getting an answer. It's about finding the real question.

@nav
  self: /lesson-3.agent
  parents: [/.agent]
  peers: [/lesson-0.agent, /lesson-1.agent, /lesson-2.agent, /field-notes-001.agent, /about.agent]