Second Brain Challenge · about five minutes

    Teach your AI once. See it twice.

    Bring one rough draft. Agree on what good means to you, then see whether your AI can use that standard on a new piece of work without a second briefing.

    See the test prompt

    No signup  ·  Your draft stays in Claude or ChatGPT  ·  You use your own AI account

    Trial signalyour correction → three standards → fresh work

    A representative example

    The useful part happens before the rewrite.

    Use a real draft in the challenge. This fictional LinkedIn example shows the difference between fixing one answer and agreeing on what good should look like.

    What you bring

    A generic draft

    “AI is changing how we work. The people who use it best will save time, stay ahead, and achieve more.”

    Your correction: “This has no point of view. It could have been written by anyone.”

    What you confirm

    Three standards

    1. 01
      Name the working tension

      Do not open with a broad claim about AI changing work.

    2. 02
      Use one observed scene

      Give the reader a real situation they can picture.

    3. 03
      Stop before the lesson

      Do not force a motivational ending.

    This is the useful part to reuse. Your first draft is no longer needed.

    What you test next

    A fresh assignment

    “Write a post about why people call an AI output ‘helpful’ and still do not use it.”

    Pass condition

    The new post uses the same three standards without asking you to explain them again.

    The artifact

    Paste this. Then use the work you actually care about.

    You remain in control of the context. The prompt asks the model to make the standards visible before it writes, so you can reject weak assumptions early.

    Open Claude Open ChatGPT
    Copy-ready promptAbout 5 minutes

    Use this in a new conversation. The prompt asks for agreement before it asks for output.

    The method

    One correction becomes a small piece of working context.

    1. 01

      Show the miss

      Paste the draft and say what does not work.

    2. 02

      Set the standard

      Confirm or correct the three standards.

    3. 03

      Repair once

      Let it revise the original draft using those standards.

    4. 04

      Test twice

      Give it related work and look for the standards again.

    The second output is the proof

    Did it use your standards on fresh work?

    This page never sees the work. This is a simple self-check after you test it in your own AI client.

    Look for the standards being reused, not merely a nicer second answer.

    Before you start

    A few honest answers.

    Is this a connector or an MCP?
    No. This is the smallest possible test. You copy one prompt into the AI client you already use.
    Where does my draft go?
    Only into the Claude or ChatGPT conversation you choose. This page does not receive your draft, correction, standards, output, or Brain Seed.
    What should I bring?
    A real draft you would not send: an email, a LinkedIn post, a proposal paragraph, meeting follow-up, or short decision note.