In partnership with
Is your business built for freedom or frustration?
Take my 2-minute “Unscale Me” quiz to find out what’s blocking your path to a calmer, more profitable solo business, and get clear next steps to fix it.
Help us make better ads
Did you recently see an ad for beehiiv in a newsletter? We’re running a short brand lift survey to understand what’s actually breaking through (and what’s not).
It takes about 20 seconds, the questions are super easy, and your feedback directly helps us improve how we show up in the newsletters you read and love.
If you’ve got a few moments, we’d really appreciate your insight.
I got meta this week.
Nothing to do with Zuckerbug.
But I did use AI to analyze how I use AI.
Last week I spent two hours helping a consultant turn 80 pages of notes and dozens of source documents into a client-ready report in about 2 hours using AI.
Then I took the transcript of that call and had AI analyze my process, extract the framework I was using and name it.
Basically turning it into something I could teach, refine, turn into products, etc.
Here’s the Process
The whole process is pretty simple once you see it.
Step 1: Ask AI to Build the Analysis Prompt I didn't know the best way to analyze the transcript, so I asked ChatGPT to help me create the right prompt first.
"I have a transcript of me doing [type of work]. Help me create the right prompt to analyze this transcript and extract the framework I'm using."
ChatGPT suggested what to look for, how to structure the analysis, and what output format would work best.
Step 2: Extract the Framework I pasted the transcript and used the prompt ChatGPT created.
It identified:
The specific steps I followed (that I couldn't see myself)
What I did that most people struggle with
The sequence that made it work
Why it was effective
The framework it identified was:
Working name placeholder: AI-Assisted Synthesis for Consultants
Steps:
Define the AI’s Role and Success Criteria
Lock the Structure Before Writing Anything
Actively Correct and Re-Anchor as You Go
Draft One Section at a Time, in Order
Synthesize at the End (Summary and Recommendations)
Step 3: Name the Framework Raw analysis is useful but hard to remember. So I had AI turn it into a clean, named system with memorable step names.
I asked for 3 options, picked one, and now I have a framework I can actually use.
Here’s what I got for my own named framework:
AI Co-Consultant Method
These are the five steps:
Define – set role and outcome
Structure – lock the logic first
Anchor – constrain sources and facts
Draft – write sequentially
Synthesize – summarize from reality
My Take
I knew I had a fairly systematic way of using AI. I've used it on dozens of projects.
But I'd never taken the time to actually analyze it or make it repeatable.
It was just... the way I work.
And that's the problem with most expertise:
You know what you do works, but you can't quite explain it. The steps exist, but they're fuzzy.
It's hard to teach because it's hard to articulate. This wasn’t AI inventing my system.
It just helped me see it clearly and organize it into something I can actually use:
to better understand what you do
to create products like pdfs and courses
to teach others your framework
to form the basis of a coaching program
to refine it over time
Dig Deeper
👉 Get the Framework Extraction Prompt Pack - 5 prompts to turn your work into products you can sell. These prompts take a few steps further than what I shared above. All the way to creating a detailed outline of a 15-25 page pdf you can sell for $7, $17 or $27.
You’re brilliant on calls. Why do your emails sound flat?
I built a system that turns one coaching call into weeks of emails using your actual words. No blank page. No AI slop. Just your real thinking, extracted.
What did you think of today's edition?
Were you forwarded this email? Click here to subscribe.