Hello go-to-market (GTM) leaders, strategists, and innovators! 👋 Thank you for dropping by to learn practical AI applications and gain strategic insights to help you grow your business and elevate your team’s strategic value.
Quick Take
I uploaded a marketing strategy document to AI and asked it to build me a sales training tool. A few minutes later, I had a working simulator where two AI personas debate each other in real time. One plays the skeptical buyer using real pain points. The other plays the sales rep using actual messaging. Then it coaches you on what the rep did well and what they missed.
This is what I’m calling a thinking system. It’s AI using AI. You set up the scenario, and AI-powered personas call AI to generate each response in real-time. You’re not driving the conversation. You’re watching AI talk to AI while you learn.
This kind of work wasn’t possible before because the economics didn’t make sense. Now you can build it in minutes without developers.
Key Takeaways:
- AI can now build applications that have AI reasoning inside them. Describe what you want, upload a document, and get an interactive system where AI powers the experience.
- There’s a meaningful difference between knowledge tools (you drive the conversation) and thinking systems (AI invokes AI while you observe and learn).
- Strategy docs, playbooks, and research reports can become thinking systems that train, coach, and challenge your team.
- Start with documents your team created but rarely uses. They’re full of expertise waiting to be activated.
AI Video Explainer and AI Podcast Versions of This Newsletter
To support different learning styles, this newsletter is available as an 6-min AI video explainer (see below) and a 12-min AI podcast with two AI hosts. If you haven’t seen these AIs in action, they’re worth a view. The tech is advancing in amazing ways. I used Google’s NotebookLM to create these and personally reviewed them for accuracy and responsible AI use.
Captions are auto generatedPlayAI Video Explainer
Watch This
Two AI personas. One strategy document. A live debate that’s different every time you run it.
I used Claude for this example. ChatGPT and Gemini have similar capabilities but ways to share the output may vary. The specific tool matters less than understanding what’s now possible.
See the 3-min video of the Sales Debate Simulator in action below.Play
Prefer to scan? Here are the screenshots.
Look at the specificity. Alex opens with classic buyer skepticism: thirty minutes before another meeting, current setup works “reasonably well.” Jordan doesn’t pitch features. The rep probes for pain points and learns Alex is balancing cost control with traveler satisfaction.
The conversation evolves naturally. Pushback on ROI claims, concerns about IT strain, questions about implementation. Jordan responds with metrics, case studies, and a 4-6 week timeline with minimal IT involvement.
Run it twice and you’ll get a completely different conversation. That’s because each response is a live AI call. The personas aren’t following a script. They’re invoking AI to generate every line in real-time.
All of that came from the strategy document. The AI improvised a realistic discovery call on the fly.
And then it coaches you. The simulator produces a scorecard: what the rep did well (mirrored communication style, asked strategic questions, offered credible proof points), what they missed (no urgency, didn’t qualify budget, weak transition to pricing), and suggested next steps (reference call, ROI analysis, pilot proposal).
This is coaching you can run a hundred times.
Try the Sales Debate Simulator yourself.
What’s Actually Happening Here
A few things worth naming.
The document came alive. This wasn’t a chatbot that answers questions about the strategy. This was two AI personas using that strategy to have a realistic conversation with each other while I watched.
The AI built a thinking system. I didn’t write code. I didn’t hire a developer. I described what I wanted, uploaded a document, and got an application where AI invokes AI. Each persona’s response is a live AI call. That’s why every run is different. It’s not scripted.
This is new work, not faster work. Nobody was running persona-based debate simulations before. The economics didn’t work — hire actors, schedule workshops, fly people to training. Now it takes minutes and runs as many times as you want.
About the Strategy Document
Acme Company is fictional, but everything behind it is real.
The personas, pain points, and objections come from actual B2B buyer research. The messaging, positioning, and competitive differentiation are pulled from a real marketing strategy document that I anonymized for this demo.
Here’s what was in it.
What Else You Could Build
The debate simulator is one example of a thinking system. Before we explore more possibilities, it helps to understand the distinction between two types of tools you can create from your documents.
Knowledge Tools (Chat-Based)
Knowledge tools like custom GPTs are powerful on their own—assessing, creating, advising, chaining together. Here’s what your existing documents could become:
Want to explore this further? Check out A Leader’s Playbook newsletter on custom GPTs. The End of Handoffs introduced connecting or chaining AI teammates together.
Thinking Systems (AI-Powered)
Thinking systems take it further. It’s AI using AI. You set up the scenario, and AI-powered personas interact with each other, each response generated by a live AI call. You’re not driving. You’re observing, learning, and getting coached.
With knowledge tools, you drive. With thinking systems, you step back and watch AI talk to AI.
Jennifer Pockell Dimas, Chief Marketing & Experience Officer at Telarus, put it this way:
“Our teams spend so much energy creating sales playbooks, selling assets and competitive battlecards. Then they live in a folder somewhere. I love the idea that those same materials could become practice environments where reps build real skill is a fundamentally different return on that investment.”
Why This Matters for Your Team
The Sales Debate Simulator wasn’t about making an existing task more efficient. There was no existing task. This is new work that creates new value.
That’s the shift worth paying attention to. We’ve spent the past two years learning how AI can accelerate what we already do. Write faster. Research faster. Summarize faster.
But the more interesting question is what work becomes possible that we couldn’t do before. Decisions improve when you can simulate them first. Skills develop when practice is free.
Mary Gilbert (Kerford), Founder of InfiniteEdge, has seen several waves of marketing transformation. This one feels different to her:
“Every transformation wave I’ve seen changed what we could measure or automate. This one changes what we can build. When your intellectual property becomes infrastructure that develops your team, you’re playing a different game.”
The companies that figure this out won’t just be more efficient. They’ll be doing work their competitors haven’t imagined yet.
The companies that figure this out won’t just be more efficient. They’ll be doing work their competitors haven’t imagined yet.
Try It Yourself
Start simple. The key is having a solid foundational document to feed AI. Garbage in, garbage out.
Here’s the prompt for the Sales Debate Simulator:
"Please build a simulator where two AI personas have a live conversation with each other based on the attached marketing strategy document. I want to watch them talk, not participate. Each conversation should be unique. At the end, give me coaching notes on what worked and what didn't."Here’s another idea. A Buying Committee Simulator. It simulate a group demo with 3-4 stakeholders at once (eg., IT Manager worried about integration, Finance Manager focused on ROI, Travel Manager wanting ease of use). They interrupt each other, have side conversations, and you watch the sales rep try to satisfy everyone.
Then it gives an assessment of who’s bought in and who’s not after the meeting and why.
"Please build a simulator where an AI sales rep presents to a buying committee of 3-4 AI stakeholders (use the personas from the doc). They should react, interrupt, ask tough questions, and debate each other. I want to watch, not participate. At the end, show me which stakeholders are sold, which aren't, and why."Here’s Claude’s rendition of a Buying Committee Simulator. Try it yourself.
Below are screenshots of Buying Committee Simulators from ChatGPT and Gemini:
The first version won’t be perfect. AI is a starting point, not an ending point. Review what it builds, test it against your needs, and refine from there.
A note on what you upload: be thoughtful about the documents you share with AI tools. Avoid sensitive customer data, confidential financials, or anything under NDA unless you’re in an enterprise environment with appropriate protections. When in doubt, anonymize first.
And remember, these tools are guides for practice and reflection, not replacements for real customer conversations. Use them to sharpen your thinking, then go have the actual conversations.
Where This Is Heading
The people building this muscle memory now will have a significant advantage as AI capabilities expand. Learning to think in terms of “what thinking systems could I design?” rather than “what tasks can AI do for me?” is the skill that compounds.
The document you wrote last quarter doesn’t have to stay static. It can become a system that trains, coaches, and challenges your team every day.
That’s not a small upgrade. That’s a different category of value.
The Practical AI in Go-to-Market newsletter shares learnings and insights in using AI responsibly. Subscribe today and let’s learn together on this AI journey.
For applied learning: Explore our applied AI workshops, offering both strategic sessions (use cases and roadmaps) and hands-on building (create AI teammates and workflows during the workshop). You’ll leave with either a clear plan or working solutions.
For team transformation: See real examples—a lean GTM team’s step-by-step playbook and a global cybersecurity leader scaling to 150+ marketers with 57 AI teammates integrated into daily workflows.
For speaking: Here are virtual and in-person events where I’ve covered a variety of AI topics. I’ve also keynoted at many organization and corporate-wide events.
Whether through the newsletter, multimedia content, or in-person events, I hope to connect with you soon.