Turn What You Already Know Into a Framework You Can Teach (or Sell)
AI Makes it Easy
You have systems you use every day that you can’t quite explain.
You know they work. You’ve done them dozens of times. But when someone asks “how do you do that?” you fumble through a vague explanation.
Your best expertise is invisible to you.
This is a problem if you want to teach, sell, or scale what you know.
The Call That Changed This
A while back, I spent two hours on a Saturday call with a consultant friend. He had 80 pages of field notes from a $30K project and asked for help to turn them into a client-ready report using AI.
I walked him through my whole process. Set up the project environment. Wrote the system prompts. Built the outline. Drafted section by section. Validated as we went.
A couple days later, I realized: that was a complete A-to-Z walkthrough. Clear starting point, clear output. Everything someone would need to understand how I did it.
But I was lazy and didn’t want to spend time breaking down what I did into discrete steps.
I Used AI to Analyze How I Use AI
So I tried something: I uploaded the transcript to Claude and asked it to identify the steps I followed in that process, and turn that into a repeatable framework.
I didn’t know the best way to analyze a transcript, so I started by asking Claude to help me create the right prompt first:
“I have a transcript of me helping someone create a consulting report using AI. Help me create the right prompt to analyze this transcript and extract the framework I’m using.”
Claude suggested what to look for, how to structure the analysis, and what output format would work best.
Then I pasted the transcript and used the prompt Claude 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
After some back and forth, we landed on a 5-step framework: Prepare, Plan, Execute, Iterate, Complete.
Five steps that made sense when you said them out loud.
Before: a vague sense that “I have a process for this.”
After: a named framework I can explain in 30 seconds.
Why This Matters More Than You Think
Here’s something I didn’t fully appreciate until I went through this:
A named framework has leverage. An unnamed process doesn’t.
When your expertise is invisible, you’re stuck. You can do the work, but you can’t:
Teach it to anyone else
Package it into a product
Explain it in a sales conversation
Train a team on it
Improve it systematically
You just “know how to do the thing.”
That’s fine if you want to keep doing the thing yourself forever. But if you want to scale your knowledge, create products from your expertise, or build authority around what you do, you need to be able to articulate it.
The difference between “I’m good at this” and “here’s exactly how to do this” is the difference between a skill and an asset.
What One Extracted Framework Became
From that one transcript and one AI analysis session, I created:
A YouTube video showing the extraction process. A 20-page framework guide with templates. A low-ticket product to test interest. Multiple newsletter issues (including this one). Credibility to pitch training to the consultant’s company (which led to a capacity-building engagement with the owner’s daughter-slash-operations manager, and THAT helped me clarify a lot of things about what direction I should be going).
Everything is content. But first you have to extract the pattern.
One Saturday call became the foundation for weeks of content and a potential new revenue stream. Not because I did anything special on that call. Just because I finally took the time to name what I was already doing.
The Extraction Process (Step by Step)
Here’s exactly how to do this with your own work.
Step 1: Capture the Raw Material
You can’t extract a framework from work you didn’t capture.
Record your calls (with permission). Save transcripts. Keep the messy notes from projects where you got results.
The best candidates are complete walkthroughs: A-to-Z processes with clear starting points and outputs. Client calls where you explained your whole approach. Projects where you can trace the full arc from problem to solution.
If you don’t have transcripts, start recording now. Most video call tools (Zoom, Google Meet, Riverside) have built-in transcription. Turn it on.
Step 2: Ask AI to Help You Build the Analysis Prompt
Don’t just dump a transcript into Claude and say “extract the framework.”
Start by asking AI to help you create the right prompt:
“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.”
AI will suggest:
What to look for in the transcript
How to structure the analysis
What output format will be most useful
This meta-step matters because you don’t know what you don’t know. You’re too close to your own process to know the best questions to ask about it.
Step 3: Run the Analysis
Paste the transcript and use the prompt AI created.
You’re looking for:
The specific steps you followed
The sequence that made it work
What you did that most people skip or struggle with
The underlying principles (even if you never stated them explicitly)
Why was it effective
Don’t accept the first output. Ask follow-up questions:
“What patterns do you see in how I handled [specific challenge]?”
“What did I do differently than someone might typically approach this?”
“What’s the underlying principle behind step 3?”
Keep refining until you have something that feels true to what you actually do.
Step 4: Name It
Raw analysis is useful but hard to remember.
Ask AI to turn the analysis into a clean, named system with memorable step names:
“Turn this framework into a named system with 3-5 clear steps. Give me a few naming options for the overall framework and for each step.”
Review the options. Pick one that:
Makes sense when you say it out loud
Is easy to remember
Captures the essence of what makes your approach different
Wrestle with it until it clicks. This is the part where you add your judgment. AI can suggest, but you decide what actually represents your work.
Step 5: Document It
Once you have a named framework, write it up properly:
What problem does this solve?
Who is it for?
What are the steps?
What does each step involve?
What are the common mistakes at each step?
What does success look like?
This documentation becomes the foundation for everything else: products, training, content, and sales conversations.
Step 6: Turn It Into Something
One framework can become:
A PDF guide or ebook
A course or workshop
A series of newsletter issues
A YouTube video or tutorial
A training offer for companies
The foundation of a coaching program
You’re not starting from scratch with any of these. You’re just translating the same framework into different formats for different contexts.
The Prompts I Used
Here are the actual prompts that worked for me:
To build the analysis prompt: “I have a transcript of me helping a consultant create a report using AI. Help me create the right prompt to analyze this transcript and extract the framework I’m using.”
To extract the framework, I used the output from the previous step.
To name it: “Turn this framework into a clear, named system. Give me 3 options for the overall name and suggest memorable names for each step. The names should be easy to remember and capture what makes this approach different.”
To document it: “Help me write up this framework as a guide. Include: what problem it solves, who it’s for, the steps with details, common mistakes at each step, and what success looks like.”
Start With Your Last Win
You don’t need to wait for the perfect project.
Think about the last time you helped someone get a result. The last client call where you walked through your whole process. The last project when someone said, “How did you do that?”
That’s your starting point.
Record it. Transcribe it. Ask AI to extract the pattern.
Your best systems are already inside your work.
The expertise is already there. The framework extraction is just making it visible.