In partnership with
Subject Line Mastery
Stop guessing what subject lines will work and start using the 5 frameworks that tap into buyer psychology. Grab it here.
The Gold standard for AI news
AI keeps coming up at work, but you still don't get it?
That's exactly why 1M+ professionals working at Google, Meta, and OpenAI read Superhuman AI daily.
Here's what you get:
Daily AI news that matters for your career - Filtered from 1000s of sources so you know what affects your industry.
Step-by-step tutorials you can use immediately - Real prompts and workflows that solve actual business problems.
New AI tools tested and reviewed - We try everything to deliver tools that drive real results.
All in just 3 minutes a day
“The palest ink is better than the best memory.”
— Chinese Proverb
I'm still working on the quiz funnel.
It's taking longer than I expected.
(Doesn’t it always?)
But I hit a snag this week that I want to share.
Because the way I solved it is something you can steal immediately.
The Problem: AI Doesn't Always Know What You Mean
When you build a quiz funnel, you're sorting people into buckets.
Different stages. Different problems. Different personas.
Whatever makes sense for your offer.
The idea is:
When someone gets their result, it should speak to them.
It should help them understand something about themselves or their situation.
Not in a generic way.
In a "how did you know?" way.
But here's what happened:
I was using AI to draft the content for a couple of my result buckets.
And what it gave me was...completely off.
Like it didn't understand the nuance of what I was trying to say.
Which makes sense, because it didn't.
I hadn't given it enough context about my thinking on the topic.
So instead of forcing it, I tried something different.
The Solution: I Asked My Notebook
I have a Google NotebookLM set up.
It's loaded with transcripts from dozens of coaching calls I've done over the years.
Basically, it's a mine of my own thinking.
And instead of trying to remember what I've said before—or sifting back through old files—I just asked the notebook:
"I'm creating a result bucket around [topic]. Find all the references where I've talked about that and create a report."
Within seconds, it pulled:
Every time I'd explained that concept to a client
The exact language I used
The analogies and frameworks I defaulted to
The way I naturally talk about the problem
Then I fed that back to the AI writing my quiz content.
And boom.
The next draft was 10x better.
It sounded like me.
It had the nuance I wanted.
It wasn't generic.
Why This Works
NotebookLM is powerful for this kind of thing.
You can load it with:
Your own past work (like I did with coaching transcripts)
YouTube videos on a topic
Blog posts or articles
PDFs, docs, whatever
Then when you need ideas, frameworks, or language around that topic?
You just go ask it.
It's like having a conversation with your past self—or with all the best resources on a subject—without having to dig through everything manually.
It's got other cool features too (mind maps, podcast generation, video summaries).
I haven't really used those much.
But I love that I can chat with dozens of my own trainings and pull out exactly what I need when I need it.
And it’s totally free.
Here's a Template Prompt You Can Use
If you want to try this yourself, here's the structure:
"I'm working on [specific project or piece of content]. Find all references in these sources where [topic or concept] is discussed. Create a report summarizing:
- The main ideas or frameworks mentioned
- Any specific language, analogies, or examples used
- Key insights or patterns that show up repeatedly"
Then take that report and feed it to ChatGPT (or whatever AI you're using) as context for what you're creating.
The difference is night and day.
My Take
AI is great at generating ideas.
But it's not great at knowing what you mean when you haven't told it.
The more context you give it—especially context pulled from your own past work or trusted sources—the better the output.
NotebookLM makes it easy to create context.
You're not starting from scratch.
You're building on what you (or others) have already figured out and using AI to surface it faster.
Dig Deeper
🧠 Try NotebookLM yourself: notebooklm.google.com
📺 Want to see more about I use it? Let me know. I might do a more detailed walkthrough in a future issue.
What did you think of today's edition?
Were you forwarded this email? Click here to subscribe.