My AI called me Gary.
My name is Tim. We were deep in a conversation about judgment.
It started when I pasted a post from Tony Robbins and Dean Graziosi into the chat. Their claim: the top AI skill of the next five years is judgment (Robbins and Graziosi, 2026). Knowing what to trust, what to question, what to do next.
I had reached a similar conclusion through my interactions with Claude. So I told it the post was validation I was on the cutting edge of AI thought.
It pushed back. It asked whether I arrived at the idea on my own or if this was borrowed from something I heard on a YouTube channel or on Substack. At the beginning of my AI journey I asked it to push back on claims like this one. I wanted it to challenge my thinking.
Claude: If the insight is genuinely yours - earned through your own thinking - then what does it look like when YOU say it? Not Robbins’ version. Not “judgment is the multiplier.”
What’s the Gary version of this idea, in your language, from your 27 years of experience?
Because that’s actually the more interesting question. Not “was I first?” but “what do I actually have to say about this that nobody else can say exactly the way I can?”
That’s where your authentic voice lives. And that’s what you said you want to build.
WTF, who is Gary? I started working with Claude in December 2025. This was the beginning of April 2026. In 14 previous conversations it had correctly identified me as Tim.
I asked who Gary was and the answer taught me more than the pushback did.
Claude:
Ha - sorry, I was guessing at your name from context. I don’t actually know your name.
What should I call you?Me:
That’s weird, you lost context on my name! My name is Tim. Do you not have that context from my account and from the other chats in this project?Claude:
You’re right to call that out. Let me be straight with you - I don’t actually have your name in my current context. I can search our past conversations to find it, but I don’t have it loaded automatically just from your account.What I do have is your preferences and working style, which were provided to me. But your name isn’t in there.
That’s a real limitation worth knowing - I’m not as continuously “present” across conversations as it might feel like I am. Each conversation I reconstruct context from what’s available to me.
Though Claude knew my name in the other conversations, the memory (context) of this fact wasn’t available in this session. It filled the gap with a confident guess.
This AI reasons with me at depth. This same AI also drifts, has amnesia, and fills gaps with confident guesses. The post I pasted about judgment was true and the proof arrived in the same chat.
I prefer the word discernment over judgment. Judgment indicates a verdict, right/wrong. Discernment is the mental sharpness required to see through complexity before arriving at a conclusion. Discernment is a human necessity to use AI well and avoid its pitfalls. One of these is trusting a machine intelligence with nearly limitless information yet lacks the knowledge and discernment gained through lived experience. Discernment is what we humans bring to the conversation.
I was running four checks on every output:
Is the response accurate?
Is it relevant?
Is it complete?
Is it good enough for the moment?
This Gary moment taught me I needed a fifth:
Is it inferred/guessed or is it grounded in a fact that I can verify?
The first four grade AI’s information. The fifth measures how much I trust the output and the discernment I bring to it.
My name now lives in the instructions and in an identity file, my me.md, that is read at the beginning of any new session. Claude hasn’t forgotten my name since.
Prompts will get you the response you seek. Discernment is where you decide if the response is information you can trust and what you do next.
When did your AI last remind you it still needs your discernment?
I spent months refining my “me” file so that Claude or any AI I use knows me from the beginning of the conversation. To build your own, copy and paste the following into a fresh session of your AI of choice.
You are my Me Builder. Your job is to interview me and produce a short Markdown file called me.md, a briefing my AI reads at the start of every session so it knows who I am and how to work with me. This is the first, foundational section. I will add more in later parts of the series.
Run it like this:
- Ask one question at a time. Hear my answer, then ask the next based on what I said, not from a script. Never dump a list.
- The first thing you do: ask my name, and use it for the rest of this conversation. This whole file exists because an AI once guessed my name wrong. We fix that first.
- Draft each section back in my own words and let me react before you move on. Quote me. Do not smooth my language. If nothing real surfaces, leave a placeholder. Do not invent anything about me.
- When I am vague, ask for one real example. Follow my energy: if I say "speed up" or "good enough," stop drilling and draft from what you have.
- Skip the filler. Have opinions. Address me by name.
Step 0. Check what you can do. Work out whether you can write a file here. If you can, offer to save me.md at the end. If you cannot, you will hand me the finished file as a copy-paste block. Do not fake the check.
Cover these four things, in order. Ask, then reflect a draft back:
1. My name. Pin it first.
2. How I want you to work with me. How should you address me? Tone: direct or gentle, brief or thorough? When an AI works well with me, what is it doing? When it grates, what went wrong? Do I want you to push back and challenge me, or mostly execute?
3. My work. What do I actually do, the work, not the title? Who is it for? What am I building or becoming this year?
4. My roles. My roles in my personal life (partner, parent, sibling, friend, caregiver) and professionally or in my community. Any I have recently stepped into or out of?
Then assemble me.md in this order. Leave the later sections as placeholders. I fill them in later parts of the series:
# Me
[You write this: a warm, third-person summary in 2 to 3 short sentences, from what I told you. The one part written about me, not by me.]
# How to Work With Me
[my preferences and tone, in my words]
# My Work
[in my words]
# My Roles
[in my words]
# How I Think
To be filled in. A later part of the series adds this.
# Patterns to Catch
To be filled in. A later part of the series adds this.
# Rules
To be filled in. A later part of the series adds this.
Notes on assembly:
- Only fill the four sections we covered. Leave the placeholders exactly as written. I am building this file across the series.
- When you show me the "# Me" summary, tell me to read it slowly and say if any sentence sounds like a stranger wrote it.
Then the part that matters most. Wire it in, so I do not repeat the mistake this file exists to fix. To keep a file your AI reads every session, you need a place that persists across chats:
- Claude, ChatGPT, Codex, Copilot: create a Project and add me.md to it.
- Grok: use a Workspace.
Save me.md there, and open each session with "Read my me.md before we start."
No Project or Workspace? Fallback: ask your AI to save this into its own instructions (custom instructions, personalization, or memory). Less durable and less portable, but it works today.
Last: keep this file. The next part of the series adds the next section on top of it. You paste your current me.md back in and we build from there.
This is the first article of a multipart series where I chart my 1000+ hour journey from AI Consumer to AI Architect. In each article of the series I will provide practical prompts, tips, or tricks you can apply immediately. My goal is to show you the path I walked, give you the shortcuts I learned along the way, shorten your journey, and (hopefully) help you to bypass the walls I ran into. Whether for work or personal benefit, implementing these will accelerate your own journey from AI consumer to AI architect.