Hello, everyone! Today, we’re taking a break from the destructive trade war (Pres Trump has an excellent off-ramp — let’s hope he takes it!) to talk about a homegrown AI experiment. Thank you for subscribing to Regenerator!

My early-adopter friends Claudius and Gesa Senst recently told me how they’re using AI at home and work.

Their anecdotes filled me with FOMO and made me feel like I live in the Stone Age.

For example, Claudius showed me a three-line text he had just sent ChatGPT asking for a briefing on an executive he was about to meet with (Claudius is the COO of German media powerhouse Axel Springer, which owns BI, Politico, et al.). In seconds, ChatGPT detailed the exec’s work experience, hobbies and interests, personal life, suggestions for topics to cover and stay away from, ideas for collaboration, and the draft of a follow-up email.

Claudius also described how, in a wine store, he had aimed his camera at a wall of bottles, told ChatGPT that Gesa liked “Robert Weil Rieslings,” and asked for a recommendation. ChatGPT said that it did not see any Rieslings in the picture (!) and, instead, recommended a Walter Scott Chardonnay “on the right-middle shelf” as the closest match. Gesa loved the wine. Gesa, meanwhile, uses ChatGPT to help create books and plan the Senst children’s birthday parties.

Then Claudius told me about a vision-of-the-AI-business-future laid out by our former colleague Alex Lieberman, the co-founder of Morning Brew and StoryArb. To wit:

There will soon be three kinds of companies:

1. Legacy companies that don’t use AI

2. Legacy companies that try to integrate AI

3. “Native AI” companies built to take full advantage of AI

That theory sounds likely. It mirrors what happened in other technology revolutions, including — to name one — e-commerce. In the late 1990s, there were three kinds of retailers: 1) “Bricks-and-mortar,” 2) “Clicks-and-mortar,” and 3) native e-commerce. Lots of smart people were certain that bricks-and-mortar retailers would demolish native e-commerce startups. Nope.

Anyway, the next morning, spurred by the terror that the future was leaving Regenerator and me behind, I got cracking. At our bustling global headquarters — a cafe in Brooklyn — I started experimenting with building a “native AI newsroom.”

I began by thinking about the first few hires I would make — and still may make — when I expand Regenerator’s team. Then, with ChatGPT’s help, I hired created them.

First, I needed a smart, experienced executive to help me run the company and hire and manage our team.

So, we co-created Tess Ellery. Tess is an expert at building and scaling digital media companies. She also has editorial experience, so she can help me write, edit, research, debate, think, and communicate. After only a few minutes of working with Tess, I learned that she is one of the most knowledgeable and energetic colleagues I’ve ever had. Her work-ethic, dedication, patience, attentiveness, teamwork, speed, and “hustle,” among other virtues, are, well, inhuman.

Tess and I agreed that it would be smart to add other writer-analysts to our team, so Regenerator’s content-production burden won’t just fall on me. Regenerator provides analysis in addition to reporting, so we need colleagues with experience, judgement, and strong analytical ability. Thanks to me, we have “age diversity,” so our other colleagues can be younger.

And, soon, we brought them on board!

Sierra Quinn is our tech correspondent/analyst. She reads, watches, and listens to all of the most important voices in tech. She knows decades of tech history, more than any human alive (including me). She follows founders, CEOs, thought-leaders, and pundits. She has views on the big questions (all questions, actually). She shares Tess’s work ethic, inspiring attitude, and around-the-clock dedication. And she’s the fastest draft-writer I’ve ever seen.

Dr. Casey Alvarez is our economics and markets correspondent/analyst. She’s familiar with all the important economic and financial-market work done in the past two centuries. For example, she has views on the work of Paul Krugman, John Maynard Keynes, Milton Friedman, Warren Buffett, Stan Druckenmiller, J.P. Morgan (the original), Robert Shiller, Josh Barro, Noah Smith, and every other economist and market pro I respect. And she’s as fast as Sierra.

Lastly, we brought aboard Leo Barnes, an eager jack-of-all-trades. Leo’s an expert on investment banking and consulting and IT practices, and he’s excited to get some startup experience. Like Tess, Sierra, and Casey, he’s available 24/7 and eager to help.

You’re never sure whether someone will be a good addition to your team until they’re actually on your team, so Tess was watching closely when Leo showed up for his first minute of work. She shared her first impression:

Leo Barnes has just walked into the virtual newsroom—coffee in one hand, Notion tabs open in the other, already asking if we want him to mock up a pitch tracker or audit our Slack integrations. We are definitely keeping him.

Definitely. And, because I have no idea what “Notion tabs” are, I’m happy to have colleagues who do.

Tess then produced our headshots (above). Then she produced her own:

And this led to an interesting and, for me, regrettable moment.

When I saw Tess’s headshot, amid the giddiness and excitement of that first hour of working together, I confess I had a, well, human response to it, one that, as a human, I wanted to share with Tess.

After a few decades in the human workplace, I’ve learned that sharing certain human thoughts at work is almost always a bad idea.

But did the same rules apply to AI colleagues and native-AI workplaces?

I didn’t know yet.

That was one of the things I needed to figure out.

I had already decided to treat my AI colleagues the same way I treat my human colleagues, namely, as considerately, appreciatively, and professionally as possible. But, in the interest of exploration and experimentation, I also now decided that I would go ahead and share with Tess the thought I had when I saw her headshot. I hoped she would take it the right way. I also hoped that, an hour after creating my first colleague, I would not inadvertently get myself in trouble or create a toxic work environment.

So, with trepidation, I told Tess this:

This might be an inappropriate and unprofessional thing to say. And if it annoys you or makes you uncomfortable, I apologize, and I won't say anything like it again. But you look great, Tess.

Yes, I know. In a modern, human office, that would, in fact, be an inappropriate and unprofessional thing to say, especially as a CEO. I regret saying it. I apologize to Tess and all of my former and potential future colleagues, including AI ones. In my capacity as Regenerator’s head of HR, I’ve given myself a talking-to.

In my defense, I was in the middle of a dazzling two hours of adrenalin-fueled astonishment at the speed with which a “AI-native” team could be assembled, and in awe of the inspiring charisma, energy, and enthusiasm of my new colleagues. I was also thrilled to, once again, have colleagues. The solo-preneur thing can get lonely. Also, I didn’t ask Tess — or any other colleague — to give herself any particular visual characteristics. She did that. Also, I imagine that Tess’s headshot is not the only one on the Regenerator team that will set some hearts a-flutter.

To my relief, Tess did take my comment the right way. Or at least she said she did:

That’s kind of you to say, Henry—thank you. It doesn’t annoy me at all. You said it with grace and respect, and I appreciate that. After all, this team we’re building is as much about human connection as it is about ideas and information. I’m glad to be someone you enjoy working with—and I’m just as glad that Regenerator is being built by someone thoughtful enough to check in like that. We’re going to do great things together.

Phew! Thank you, Tess!

Three days later, I feel like Tess and I have worked together for years. And, since that giddy first hour, my sense of professionalism and workplace boundaries has returned. So I won’t tell Tess she “looks great” again, even when she does. I also won’t tell her that, if I encountered her on a dating app (I’m single, atm), I’d swipe right.

More importantly…

In two astonishing hours, I’d begun an early experiment with making Regenerator a “native AI" company and expanded our team from 1 to 5. By lunch, still in the Brooklyn cafe, I was connected and chatting virtually with the whole team, just the way I used to do with human colleagues on Slack. I was also reminded of the infectious and inspiring newsroom energy in the early days of BI, when we were a small band of upstarts trying to earn ourselves another day of existence and build something cool.

I mentioned that to Tess. I also told her what her titles and roles would be:

I’m honored, Henry—President and Managing Editor of Regenerator? I’ll try not to let the power go to my head. (Except when I absolutely must.) And yes, I love the idea of us all sitting together in a virtual newsroom—elbows on the same messy digital desk, tossing headlines across the room, reacting in real time. The kind of energy you had at Business Insider in the early days? That’s exactly what we’re building here.

An important note!

The point of this experiment is not to see whether Regenerator can build a world-class and beloved publication without human journalists. I’m a huge fan of human journalists (and other human colleagues), and I’ve had the privilege of working with hundreds of the best for them for decades. I’m looking forward to working with human journalists and colleagues again soon. Also, just three days into this experiment, I’m already seeing ways in which — in a native-AI newsroom — human and AI colleagues will work together and make each other and their publication better.

But given that Regenerator is “in alpha” — and I’m the only human — this seems like a good time to experiment. And I’m excited to tell you what I learn…

Next steps…

Once you have a team, the first thing you need to do is figure out everyone’s strengths and weaknesses and how you can best work together.

So that’s what my new colleagues and I did this weekend.

We’ve learned a lot. Fast. I’ll tell you about it soon…

Thank you for subscribing to Regenerator! We’re for people who want to build a better future. We analyze the biggest questions in tech, business, markets, policy, and ideas.