Invite your heroes into your AI conversations

I had a problem.
I wanted to create a YouTube channel and had my first video ready to go, but then… nothing. Weeks passed. I had ideas, I had equipment, and I’d watched enough tutorials to edit like a pro. But I couldn’t get myself to shoot video number two.
Classic procrastination.
So I did what I often do when I’m stuck: I talked to Claude. But this time, I didn’t just ask for advice. I invited two experts into the conversation to help me figure this out.
Claude brought in James Clear, author of Atomic Habits, and Ali Abdaal, the doctor-turned-YouTuber with over 6 million subscribers. Together, they helped me design a system for creating videos consistently—the “Monday Morning Musing” format that led to the video you’re about to watch.
That conversation didn’t just shape my YouTube strategy. It’s a great example for how I’ve been approaching AI conversations differently for months now.
The average of everything
Here’s the thing about talking to an AI: you’re essentially conversing with the average of everything it was trained on. Ask about technology, and you’ll get a blend of every tech perspective in its training data. Ask about productivity, and you’ll get a mix of every productivity guru ever digitized.
It’s useful. But it’s not specific.
The typical prompt engineering trick is to say something like, “You are an expert on electric vehicles” or “You are an AI specialist.” That helps. The AI starts behaving more like someone who actually knows the field deeply.
But you can go one step further.
What if you could talk to anyone?
What if, instead of asking for “an expert,” you could invite Steve Jobs into your conversation about technology? Or Marie Curie about scientific thinking? Or your favorite author to discuss storytelling?
You can.
And the results are remarkably different from generic AI responses.
Watch a demo of this technique in my latest video, where I invite Marcus Aurelius, Marie Kondo, and Hermione Granger into a conversation about overcoming procrastination:

Why this works (and how it changes you too)
On the surface, this technique does something simple: it steers the AI away from “the average” toward a specific slice of its training data. Instead of every perspective on a topic, you get the perspective of someone whose thinking has been well-documented—through books, interviews, articles, speeches.
But there’s a deeper magic happening.
When you invite specific people into your AI conversations, you’re not just changing what the AI says. You’re changing how you think. You’re pulling yourself out of your default thinking patterns and into new, inspiring directions.
It’s like having a panel of advisors who challenge your assumptions, offer frameworks you hadn’t considered, and push you toward better results. The conversation becomes richer, more nuanced, more useful.
In “The Cybernetic Teammate”, which I found via Ethan Mollick, the researchers validate this approach: AI can complement skills in ways that help us overcome our own limitations. When I needed visual design advice for a friend’s website—a topic I’m completely unfamiliar with—I asked Claude which experts could help. It suggested Paula Scher and Kenya Hara, and their perspectives gave me frameworks I never would have discovered on my own.
How I use this technique
I’ve been using this approach for months now, and it’s become a habit. Here are some examples:
For my blog posts: Almost every article I’ve published recently involved inviting experts like Seth Godin, Simon Sinek, or Donald Miller into the editing process. They help me make the content more remarkable, more meaningful, more story-driven. (In fact, Seth, Simon, and Ali are here right now helping me write this very post! We can go full meta with this: here’s me collaborating with Seth, Simon, and Ali on this very blog post inside Claude)
For the YouTube strategy: When I couldn’t figure out how to create videos consistently, Claude invited James Clear and Ali Abdaal to help me design a low-barrier, high-consistency system.
For visual design: When helping redesign a website, I asked Claude to invite design experts. Paula Scher and Kenya Hara provided sophisticated frameworks that transformed the entire visual identity.
For creative projects: When starting a new pet project (to be announced later!), Claude invited Brian Eno to help with the creativity aspects. The conversation took directions I never would have discovered alone.
I first got this idea from Ethan Mollick’s book Co-Intelligence earlier this year, where he explored creative ways to collaborate with AI. Since then, I’ve made it a core part of how I work.
Tips for trying this yourself
Ready to invite your heroes into your AI conversations? Here’s what I’ve learned:
- Invite 1–3 people who can add skills or experience you’re missing or unsure of. More than three can become chaotic.
- Use this for diverse perspectives that help you brainstorm a broader set of ideas. The goal is to expand your thinking, not narrow it.
- You don’t have to do everything they say. Treat this as a funnel: collect the best ideas from different experts you admire, then narrow them down to your own personal style and preferences.
- Ask the AI to invite experts when you’re not sure who can help. This is a great way to learn about authors and thought leaders you didn’t know and explore their concepts.
- Let the experts challenge you. Working with virtual experts should feel harder, not easier. But the results you get should make you more proud of yourself. The goal is growth.
- Go broad and wide when inviting people: historic figures, fictional characters, contemporary leaders, famous stars, thought leaders. The more diverse, the better.
- Give as much context as you can—raw transcripts, websites you want to reference, rambling about a topic. The more you add to the conversation (including content, preferences, corrected drafts, random ideas), the more “you” the output will be.
Things to be aware of
This technique isn’t about perfect simulation. Don’t expect every expert incarnation to be flawless. The goal is to add different perspectives, concepts, and ideas in engaging and motivating ways—not to simulate Albert Einstein with 100% accuracy.
Avoid blindly following their advice. Use it as sources of ideas, as checklists to stay on top of, and as validation, while you create your own approach supported by trusted experts.
While talking to celebrities and historic figures can be entertaining, even fascinating, keep your goal in focus. Use their advice to create better results and avoid analysis paralysis. This is where having the AI as moderator can help steer the group toward action.
Your challenge
The next time you talk to your favorite AI model, don’t settle for generic responses.
Pick one problem you’re facing. Identify two experts you’d love advice from—living, dead, real, or fictional. Then simply say: “Can you invite [expert names] into this conversation to help me with [your problem]?”
The conversation that follows may surprise you.
When you try this, share your results on your favorite social media channels—link to this post so I can find you. I’m curious: Who did you invite? Why? And what happened?
The world’s greatest thinkers are waiting to talk to you. All you have to do is invite them in.
Resources
- My conversation with “James Clear” and “Ali Abdaal” about creating YouTube videos consistently
- And the conversation with “Seth Godin”, “Simon Sinek” and “Ali Abdaal” that created this very blog post
- James Clear – Author of Atomic Habits
- Ali Abdaal – YouTuber and productivity expert
- Seth Godin — Marketing expert and author of 22 books
- Simon Sinek — Optimist and purposeful leadership author
- Donald Miller — Storytelling coach
- Paula Scher — Influential graphic designer
- Kenya Hara — Graphic design professor
- Brian Eno — Musician, producer, visual artist and activist
- Ethan Mollick’s Co-Intelligence – A useful guide to working and learning with AI
- Dell’Acqua, Fabrizio, Charles Ayoubi, Hila Lifshitz, Raffaella Sadun, Ethan Mollick, Lilach Mollick, Yi Han, Jeff Goldman, Hari Nair, Stew Taub, and Karim R. Lakhani. “The Cybernetic Teammate: A Field Experiment on Generative AI Reshaping Teamwork and Expertise.” Harvard Business School Working Paper, No. 25-043, March 2025.
