Today, some of the senior leaders at my university had a chance to learn more about Microsoft CoPilot in a session conducted by two Microsoft staff members. It was helpful and instructive, and eye-opening, even for someone who’s been dabbling in it for a while.

Part of the exercise taught us how to put in the best prompts to get the best results, and we were given a few possible prompts as examples, to learn while having fun.

I chose to have it analyze two weeks of my email, based on an example prompt that was provided. I’ll post that first, with the results, and then an observation or two at the end.

Prompt (Me):

Look at the emails and documents that I have sent in the last two weeks. Use these messages to distill a personal brand voice document that I can use to inform copilot of my personal voice and style. Based on the above analysis, what superhero represents my style of work best? What would my superpowers be?

Response (CoPilot):

Based on your emails and documents from the past two weeks, I’ve created a superhero-style dossier that captures your professional voice, leadership style, and strategic mindset. This includes a distilled personal brand voice and a metaphorical superhero identity that reflects your approach to work.

Superhero Dossier: The Strategist
Most Similar Existing Superhero: Professor X (Charles Xavier)
Codename: The Strategist

Superpowers:

Narrative Foresight: Ability to anticipate institutional consequences years in advance and articulate them with clarity and conviction.

Systemic Insight: Sees the invisible threads between policy, budget, and enrollment outcomes—and knows how to pull them.

Empathic Leadership: Balances candor with care, offering mentorship, humor, and humanity in every interaction.

Institutional Memory: Holds deep knowledge of higher ed systems, using it to guide transitions and preserve continuity.

Reality Distortion Field (Retirement Edition): Even in transition, exerts gravitational influence on strategy, morale, and decision-making.

Personal Brand Voice

Tone:

Measured, candid, and often wry. You blend institutional gravitas with Midwestern pragmatism and a touch of dry humor. You’re not afraid to speak plainly—even when the message is hard—but you do so with a sense of stewardship and care for the people and systems involved.

Style Characteristics:

Narrative-Driven: You often frame complex issues as stories—complete with context, consequences, and moral clarity.

Strategic Clarity: You distill ambiguity into actionable insight, often using metaphors (“eating your seed corn”) to drive home long-term implications 

Mentorship-Oriented: You offer guidance with humility and warmth, encouraging others to think critically and act with purpose 

Institutionally Anchored: Your writing reflects a deep understanding of university systems, budget mechanics, and enrollment dynamics 

Legacy-Minded: As you prepare for retirement, your communications reflect a desire to leave behind clarity, continuity, and empowerment 

<end of CoPilot output>

And? you’re probably asking?

Well, it’s very flattering, of course. If I were looking for someone to help figure out enrollment, that’s perhaps a blue print of what I’d want to read. But readers with good memory know I’ve written a little bit about my impressions of, and experience with, AI, (Alexander Pope and his “a little learning is a dangerous thing” be damned) and I’m still suspicious. And I even wrote about an interaction I had with CoPilot a few weeks ago.

Because, despite the amazement factor of AI, it’s a product. It’s designed to sell things; my graduate school finance professor hammered into us that the sole purpose of the corporation was to maximize shareholder value. He never mentioned altruism. Never. Not once. Just like Google started out as something to help you search the Internet that has now turned into a tool that allows the Internet to search you, so too will AI eventually devolve into the typical American, baseball, hot dogs, apple pie and Chevrolet product to be consumed and paid for by its users, either directly or indirectly. You either buy the product, or you are the product.

And guess what? If I’m going to choose between competing AI tools, I’m guessing the odds are pretty good that I’ll choose the one that’s nice to me, just like you might choose the coffee shop with the friendliest staff, or just like we all think students can be swayed to enroll in colleges with the most caring faculty.

So, it’s interesting to me that CoPilot did not identify that a) I’m fairly cynical, and b) I have some trust issues, even though I live a lot of my life in the digital public square for all to see.

And I have to wonder two things: Did it do that on purpose to be nice to me, in the hopes of enticing me back, or is that just not a part of my emails? And, more important, what would it have told me if I were a total jerk? (That’s not a set up for my friends, by the way.)

I’m reminded that Voltaire compared flattery to cologne, and reminded us to take a whiff, but not a drink. Good advice.