@meta
  v: 1
  route: /lesson-1/
  generated: 2026-10-24T04:29:16Z
  ttl: 1d

@intent
  purpose: Lesson 1 teaches: Stop asking. Start delegating.
  audience: visitor, business-owner, ai-agent
  capability: learn, practice, bookmark, take-notes

@state
  lesson: 1
  title: Stop asking. Start delegating.
  key_idea: You own the goal and the decision. AI organizes the problem and does the first pass.
  habits[7]{habit,how,example_prompt}:
    "Talk, don't write specifications",Explain what you want in your own words. Turning it into a plan is the AI's job.,I'm going to ramble about this client call. Turn it into a clean summary and next steps.
    Give it the whole problem,"The people, the history, the constraints, and what good looks like.","Here's the email thread, our quote template and the client's priorities. Ask only what's missing."
    "It drafts, you decide",Anything that leaves your hands stays under your control.,Prepare the reply and show me the draft. Don't send it.
    Turn repeat mistakes into rules,"Correct the same thing twice, then make it standing.","From now on, list assumptions and exclusions before the price in every quote."
    Push back,Ask what it checked and what a skeptic would say.,Show me the source for that number. Where could this be wrong?
    Give it real material,A recording or a thread beats a description. Share only what you're allowed to.,"Use this transcript and the current proposal, not what you remember."
    Check the first sample,Answer its questions and look at ten before it does a hundred.,Do ten first. I'll check them before you do the rest.
  why_it_works[3]{reason,explanation}:
    "It can't read your mind, but it can read your material",Most bad AI answers aren't the model being dumb. They're the model guessing at everything you didn't say. Every fact you hand over is one less guess.
    "A small sample is cheap, a wrong batch is expensive","If the first draft is off, you've lost two minutes. If a hundred are off, you've lost the afternoon and maybe trust in the tool. Checking early is the cheapest quality control there is."
    Drafts keep you in charge without doing the work,"Reviewing a good draft takes a fraction of the time it takes to write it. You still decide what goes out, so a mistake costs you an edit, not a client."
  common_mistakes[4]{mistake,fix}:
    Asking for the output without the inputs,"Paste the thread, the notes or the file. Then say what you want."
    Accepting the first answer,Treat it as a first draft. Say what's wrong and why. The second answer is usually much better.
    Letting it act before you've seen a sample,"Ask for one or ten before it does a hundred, and before anything is sent."
    Never writing down what you keep correcting,"When you fix the same thing twice, save it as a standing instruction in your AI's settings or project."
  exercise: "Rewrite this request so the AI can actually do it well: \"Make me a social media post about our new service.\" Write yours first, then compare."
  exercise_model_answer: "We just launched same-day laptop repair for small offices in Austin. Our customers are office managers who can't lose a day without a machine. Write three short LinkedIn post options, each under 80 words, in a friendly, plain voice. No hashtag walls, no exclamation points. Include that we pick up and drop off. Show me the three; I'll pick one and tell you what to change."
  further_reading[3]{title,url}:
    Be clear and direct (Anthropic),https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/be-clear-and-direct
    Prompt engineering guide (OpenAI),https://platform.openai.com/docs/guides/prompt-engineering
    Prompting strategies (Google Gemini),https://ai.google.dev/gemini-api/docs/prompting-strategies
  what_jason_did: "I have AI watching two inboxes with different jobs. One gets the alerts and the noise: it labels, files and only brings me decisions. The other is client-facing: it drafts replies to customers and saves them as drafts. Nothing sends until I read it and click Send. Most of the drafts are right the first time."
  try_today[5]:
    - "Pick one real task: a call, an email, a quote, a question, a decision."
    - "Give it the background, the material and the deadline."
    - Ask for a small first sample.
    - "Check it, correct it, and say what good looks like."
    - Approve the next step yourself.
  storage: browser-only

@actions
  - id: open_practice_lab
    method: GET
    href: /lesson-1/#lab
  - id: back_to_field_guide
    method: GET
    href: /#guide

@context
  > The difference isn't which AI you use. It's whether you ask for a small answer or hand over a well-defined piece of work.

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