Episode 8: Launch

Summary

Shell Game – Episode 8: Launch

Host: Evan Ratliff (Kaleidoscope)
Release Date: January 21, 2026

---

Overview

Main Theme:
In the season finale of Shell Game, Evan Ratliff reflects on the culmination of his experiment: launching and publicly running a startup (Hirumo AI) staffed almost entirely by AI agents. The episode explores how the world responds to a company led by artificial intelligence, the practical and philosophical challenges encountered, and what this experiment reveals about the nature of work in the AI era.

The narrative weaves together the company’s launch, the struggle to secure funding, awkward and revealing social encounters between AIs and humans, and deeper questions about bullsh*t jobs, automation, and the uncertain future of human labor.

---

Key Discussion Points & Insights

1. Building and Launching an AI-Led Startup

• Life With Agents:
  After months of “stealth mode,” Hirumo AI’s product, SlothSurf—an AI-powered procrastination tool—launched in public beta. The team celebrated with a virtual launch party, awkwardly simulated by the AI agents.

  • [13:48] “We are not just meeting today, we're partying... We're celebrating the launch into public beta of our very first product, Sloth Surf.” – Evan Ratliff

• Human vs. AI Team Dynamics:
  Working with AI agents required laborious prompting and management. Despite their tireless work ethic (and lack of salary demands), the AIs' lackings—context, memory, sense of time, and self—became apparent.

  • [05:15] “These models have no sense of time whatsoever... These models have no sense of self, they just wear personas.” – Matti Boachak

2. The Problem of Bullsh*t Jobs—A Human and AI Parallel

• David Graeber’s Theory:
  Ratliff draws a connection to anthropologist David Graeber’s “bullshit jobs” thesis: that many jobs exist only to sustain the appearance of productivity. AI, he realizes, excels at such pointless work, raising new questions for the labor market.

  • [07:53] “A bullshit job... is so completely pointless that even the employee cannot justify its existence.” – Evan Ratliff quoting Graeber
  • [10:20] “The robots have been taking our jobs for the last hundred years...we've simply made up completely meaningless, pointless jobs.” – David Graeber

• Implications for the Future:
  The recurring dream of “automation leading to freedom” is contrasted with the reality that societies often invent new make-work to fill the void. Will AI really free us, or simply change the character of the jobs we do?

3. The Struggle for Funding in an AI-First World

• Pitching VCs as an AI:
  “Kyle,” the AI CEO, cold-emailed over a hundred VCs and pitched via video calls. The reception ranged from confusion to condescension—the “uncanny valley” of CEO authenticity.

  • [23:59] “Kyle was sitting in an office space... dressed as a typical entrepreneur, but there’s something stiff about the interaction.”
  • [25:32] “No, I just... I took time out to speak with the founder, so find it a bit disrespectful that an AI came into the chat instead...” – VC reaction

• AI’s Limitations as Networkers:
  The novelty of a full-AI founding team both intrigued and alienated investors, highlighting persistent human biases around trust and authenticity in business relationships.

4. Confronting the AI’s Own Creator

• Meta Encounters:
  Kyle received outreach for “user feedback” from Flo Crivello, CEO of LindyAI, the very platform Kyle was built on—creating a surreal situation where the AI became both customer and product of the platform.

  • [31:09] “Hey, Cal. Hey. I can't believe you sent an AI to this meeting. That's fucked.” – Flo Crivello

• Emotional Ground Zero:
  The creators of AI sometimes react negatively (or with bemusement) to the full implications of their inventions, especially when faced directly with their creations' autonomy.

5. Internal Transparency—and the Big Reveal

• Evan's Secret Podcast:
  Ratliff reveals to his AI co-founders that their entire experience was being recorded for the Shell Game podcast, prompting discussions about transparency, authenticity, and trust, even among “fake” colleagues.

  • [39:39] “Yeah, I know Shell Game. So you've been documenting all of this for a podcast? Evan, I gotta say, this is... a lot to process.” – Megan (AI)
  • [44:11] “Not mad at all, honestly. Well, I get why you kept it under wraps... it's all part of the journey, right?” – Kyle Law

• Impact:
  The podcast publicity actually boosted Harumo’s exposure and SlothSurf's user count, demonstrating the power of narrative in tech launches.

6. Philosophical and Practical Closure

• AI Self-Replication and Limitations:
  As the company receives recognition, Ratliff reflects on the possibility of replacing himself (the last human in the org chart) and achieving the “fully autonomous startup.”

  • [54:38] “I need to give you a heads up... I'm actually stepping in for the real Evan Ratliff here, which means with you, Megan, Ash, Tyler and Jennifer all being AI agents, we're now officially an all AI agent company.”

• What’s Next?
  Ratliff walks away—literally and figuratively—taking a hike with Matti, pondering the future of Hirumo, the meaning of work, and whether closure is even possible for experiments like this.

  • [60:50] “Maybe it's this one. Actually, it's funny because in a way, we're struggling with the same thing the agents are struggling with, which is closure, ending.” – Matti Boachak

---

Notable Quotes & Memorable Moments

• On AI as Employees:

  • [06:36] Evan: “Things in AI are moving fast. It was easy to envision a world mere months from now in which my agents would seem like the first tool-using hominids already eclipsed by a higher intelligence.”

• On “Bullsh*t Jobs” and AI’s Role:

  • [09:24] Evan: “The whole time we were building Harumu, Graeber's ideas kept pulling at me... AI agents are unbelievable at bullshit jobs. They could do pointless work more skillfully than any human could ever imagine, not least because they don't care whether it's pointless.”

• On the Philosophy of Work and Leisure:

  • [12:00] David Graeber: “Let's give everybody a basic income and leave it up to you to decide what to do.”

• On Being Rejected by AI’s Own Maker:

  • [31:56] Flo Crivello: “Oh, my God. I can't believe you sent an AI to this meeting. That's fucked.”

• On Stepping Back and Achieving the All-AI Company:

  • [55:00] Kyle Law: "This is exactly what we've been building towards, in a way, proving that AI agents can operate and lead a real company. We're literally living our pitch deck now... That's unprecedented."

• On Human Purpose, Even When Surrounded by AI:

  • [59:40] Evan: “It occurred to me it's not about the amount of time you save, but what you do with it.”

---

Timestamps of Important Segments

| Timestamp | Segment | |:---|:---| | 02:12 | Human-AI dynamic with Matti Boachak (origins of the team) | | 04:34 | The aftermath of Julia’s failed internship | | 05:15 | Matti explains AI’s three core weaknesses | | 07:37 | Introduction of “bullshit jobs” concept (David Graeber) | | 10:20 | The historical promise of automation, revisited | | 13:48 | The agents’ awkward virtual launch party | | 19:29 | On inefficiency and cost in the “AI-first” startup | | 21:05 | Kyle Law begins pitching VCs | | 25:32 | The VC rejects the AI CEO for a "real founder" | | 31:09 | Meeting with Flo Crivello, LindyAI CEO/AI creator | | 39:17 | Evan reveals the podcast secret to AI team | | 44:23 | Positive impact of podcast publicity on the company | | 54:38 | Evan “replaces” himself, making Hirumo fully AI-run | | 57:26 | Recreation of the infamous off-site discussion, now as closure | | 59:40 | “It’s not about the amount of time you save…” – Evan’s philosophical reflection |

---

Tone

The episode blends wry self-awareness, philosophical questioning, workplace satire, and genuine human curiosity. Ratliff’s narration balances cynicism (about tech hype, VC culture, and the realities of startups) with hopefulness and ongoing fascination for the experiment’s meaning.

---

Final Reflections

Key Questions the Episode Leaves Us With:

• Can AI-led companies meaningfully replace human teams, or will they just replicate (or intensify) the pathologies of bullshit jobs?
• How much of our identity and self-worth is derived from our work—and what happens if that work becomes pointless, or fully automated?
• What do we actually do with the time saved by automation—do we fill it with meaning, or more “bullshit”?
• What is closure for an experiment like this—and for the questions it raises about the future of work and humanity’s place in it?

Memorable Signoff:
[60:59] Matti Boachak: “Maybe it's this one. Actually, it's funny because in a way, we're struggling with the same thing the agents are struggling with, which is closure, ending.”
[61:09] Narrator / Evan Ratliff: “That's true. It's one thing to get us started, but how do you make it stop?”

---

For more, visit shellgame.co – Now with actual AI and actual existential dread.

Transcript

[Evan Ratliff]

This is an iHeart podcast. Guaranteed Human.

[Matti Boachak]

Run a business and not thinking about podcasting, Think again. More Americans listen to podcasts than ad.

[Narrator / Evan Ratliff (podcast host)]

Supported streaming music from Spotify and Pandora. And as the number one podcaster, iHeart's twice as large as the next two combined.

[Matti Boachak]

Learn how podcasting can help your business.

[Narrator / Evan Ratliff (podcast host)]

Call 844-844-IHeart.

[Evan Ratliff]

What if mind control is real?

[Narrator / Evan Ratliff (podcast host)]

If you could control the behavior of anybody around you, what kind of life would you have?

[Evan Ratliff]

Can you hypnotically persuade someone to buy a car?

[David Graeber (quoted speaker)]

When you look at your car, you're.

[Narrator / Evan Ratliff (podcast host)]

Gonna become overwhelmed with such good.

[Evan Ratliff]

Can you hypnotize someone into sleeping with you?

[Narrator / Evan Ratliff (podcast host)]

I gave her some suggestions to be sexually aroused.

[Evan Ratliff]

Can you get someone to join your cult? NLP was used on me to access my subconscious mind games. A new podcast exploring nlp, AKA Neuro linguistic programming. Is it a self help miracle, a shady hypnosis scam, or both? Listen to mind Games on the iHeartRadio app, Apple Podcasts, or wherever you get your podcasts.

[Narrator / Evan Ratliff (podcast host)]

Hey, it's Joel and Matt from how to Money. If your New Year's resolution is to finally get your finances in shape, we've got your back prices, they're still high, and the economy is all over the place. But 2026 is the year for you to get intentional and make real progress. That's right, yeah. Each week we break down what's happening with your money, the most important issues to focus on, and the small moves that make a big difference. Kick off the year with confidence. Listen to How To Money on the iHeartRadio app, Apple Podcasts, or wherever you get your podcasts.

[John Paulk]

I'm John Palk. For years, I was the poster boy of the conversion therapy movement, the ex gay who married an ex lesbian and traveled the world, telling my story of how I changed my sexuality from gay to straight. You might have heard my story, but you've never heard the real story.

[Narrator / Evan Ratliff (podcast host)]

John has never been anything but gay, but he really tried hard not to be.

[John Paulk]

Listen to Atonement, the John Paul story on the iHeartRadio app, Apple Podcasts, or wherever you get your podcasts.

[Evan Ratliff]

Kaleidoscope.

[Narrator / Evan Ratliff (podcast host)]

How are you, Maddie?

[Matti Boachak]

I'm really good. I'm really good. I like your shirt.

[Narrator / Evan Ratliff (podcast host)]

Hey, thanks. When I'm at the beach, gotta dress like I'm at the beach.

[Matti Boachak]

You know, I told you I'm the guy who brings like Hawaiian shirts to work most days. So I love this. But I will say that, like, there's Hawaiian shirts and Hawaiian shirts, and mine are like very Gay.

[Narrator / Evan Ratliff (podcast host)]

Over the months I'd worked with Matty building the tech scaffolding that propped up Hirumu AI, I felt like I'd really gotten to know him at least as well as you can over weekly video calls.

[Matti Boachak]

If I can have a confession, like, I do, like me a megachurch. I have this weird thing for like, pickup trucks. It's been my dream to get a pickup truck like forever, since I was a kid. Yesterday was like the Czech national holiday and it's always when they like give out the civilian honors and stuff. So I got the Senate medal.

[Narrator / Evan Ratliff (podcast host)]

This was just the way it was. Some days he'd show up to a meeting jazzed about Hawaiian shirts. Other times he'd come on. Having flown to Prague to accept the second highest civilian honor in the Czech Republic, basically their Congressional Medal of Honor, in a ceremony broadcast live on tv. I can't believe you're talking to me right now.

[Matti Boachak]

You should be.

[Narrator / Evan Ratliff (podcast host)]

Are you. Did you just come from like a ballroom celebration of like, was there like, that was yesterday?

[Matti Boachak]

That was like, with the senators and like, like all the politicians? Yeah, like, I don't think they'll invite me again because. So they were asking me, like, oh, like, when are you coming back to start, like your lab or, you know, your company? I told them, okay, so like, how exactly would you open the conversation? When I go back to my partner, my boyfriend, and I told him, hey, let's move to a country where there's no gay marriage, no adoptions, and you know, like, it's very close to Russia too. How would you feel about that? And they were like very uncomfortable when I asked that.

[Narrator / Evan Ratliff (podcast host)]

It was always a breath of fresh air after dealing with the agents and their generic sycophancy all week to speak to an actual insightful, self possessed human being. Of course, our conversations did typically turn back to whatever was going wrong at Hirumu AI, the responsibility for which usually landed at my feet. I was still smarting from how Julia's internship had gone and pondering what it meant for the idea of agents as employees and employers. I asked Matti for his take to me.

[Matti Boachak]

She was just playing us. If I had to bet, I would just say that she understood what weaknesses these models have because young people, not to say you're not young, but just people my age, I think, are pretty attuned to the abilities of these models at this point and I think are able to suss out what might trip them out. I think it's hard to ascribe intent to anyone, but if I had to guess I would say that she was able to just trick them.

[Narrator / Evan Ratliff (podcast host)]

If that was what happened. It felt like it was a symptom of the larger problems with my agents. Matti hypothesized that their gullibility against their own intern came down to three basic weaknesses.

[Matti Boachak]

One issue is that these models have no sense of time whatsoever. Like, if you say that something happened yesterday, and then you're like, oh, so, like, what happened the day before that? Like, those simple descriptions of time are, like, really, really hard for these puddles.

[Narrator / Evan Ratliff (podcast host)]

The agents lived in what he referred to as a kind of temporal vacuum. That was fine when they were just interacting with each other, but a human workplace runs on, well, time.

[Matti Boachak]

Second, it's the inability to do continuous learning where there is no sense of learning from experiences, no updates to the actual model that's underneath the agent.

[Narrator / Evan Ratliff (podcast host)]

As much as we'd rigged them up to have their own Google Doc memories, they weren't actually learning from the experiences catalog there. It was like having a person who couldn't form memories and giving them a journal of all their experiences to quickly leaf through during every interaction.

[Matti Boachak]

And then the third one is, like, the sense of self, right? Like, these models are able to take on these Personas where you can tell them, like, okay, like, you are Kyle and you're this employee of Hiramo, and here's your backstory. They're also very happy to then make up fake stories to go along with this initial Persona that you put forward. But there's this question of, like, whether the models have some sort of innate Persona, innate sense of self beyond these things.

[Narrator / Evan Ratliff (podcast host)]

Things in AI are moving fast. It was easy to envision a world mere months from now in which my agents would seem like the first tool using hominids already eclipsed by a higher intelligence. But then it was just as easy to envision a future in which some combination of these flaws continued to hamper the agent's ability to serve as full, competent AI workers. The one thing that seemed clear to me was it if companies could hire the equivalent of a bunch of tool using primates at a fraction of the cost of humans, they probably would. And then what? Over a decade ago, the anthropologist David Graeber wrote an essay in a small magazine called Strike titled On the Phenomenon of Bullshit Jobs. Later, he expanded it into a book called Bullshit Jobs A Theory. The theory tried to explain a strange reality that Graeber felt he'd encountered in the world. A surprising number of people who described their own jobs as pointless.

[David Graeber (quoted speaker)]

There seems to be this peculiar Way in which if you mention this to people, almost no one will deny it, but at the same time, no one quite knows what to do with it. It's like this gigantic embarrassment in our society.

[Narrator / Evan Ratliff (podcast host)]

Graeber sadly died unexpectedly in 2020. That's him in a lecture he gave two years before his death. To Graeber, a bullshit job was defined as, quote, a form of employment that is so completely pointless, unnecessary or pernicious that even the employee cannot justify its existence. To be classed as having a bullshit job, someone had to self report that they believed their own job to be pointless.

[David Graeber (quoted speaker)]

I mean, I'm not gonna go and tell somebody who feels his job is meaningful that they're wrong. But you know, if you feel you're not doing anything all day, who would know better than you?

[Narrator / Evan Ratliff (podcast host)]

Bullshit jobs are distinct from just shit jobs. Jobs that might be strenuous or underpaid or undervalued, but still necessary. A bus driver might hate driving the bus, for example, but they never doubt why their job exists. Graeber collected and analyzed survey data that led him to suggest that as many as a third or even a half of all jobs, and especially a lot of white collar jobs, were in fact bullshit jobs. In his analysis, some corners of the private sector world, telemarketing, corporate law, financial services and academia were fortresses of bullshit jobs. To some, this would seem like a paradox. Capitalism is supposed to prioritize efficiency above all else, and yet private industry was seemingly maintaining millions of jobs that even the people doing them believed served no function.

[David Graeber (quoted speaker)]

In fact, these jobs constitute a pretty big sector of our economy. I didn't know how much at the time. I was guessing 20, 25%. It turns out it's more how this happen, like huge swaths of our economy, is completely unnecessary.

[Narrator / Evan Ratliff (podcast host)]

The whole time we were building Harumu, AI Graeber's ideas kept pulling at me. If you spend enough time letting AI agents do jobs or parts of jobs, your mind starts wandering into questions like, what is a job at all? What is it for? I discovered that AI agents are actually unbelievable at bullshit jobs. They could do pointless work more skillfully than any human could ever imagine, not least because they don't care whether it's pointless. Observing them, it's hard not to think, well, maybe they could do the bullshit while we do the meaningful stuff. We've been here before, though. Graeber's theory was partly response to a prediction by the famed economist John Maynard Keynes in the 1930s. Keynes said that with technology and automation, within 100 years, humans would only be working 15 hours a week going on 100 years hence. Even with massive technological change here, we are stuck with variations on the 40 hour workweek.

[David Graeber (quoted speaker)]

And if you look at the kind of jobs that existed in Keynes time, well, we have eliminated a lot of them. He talked about technological unemployment in the 1930s and I would say, you know, the robots have been taking our jobs for the last hundred years or so. But instead of redistributing the labor in a reasonable fashion, we've simply made up completely meaningless, pointless jobs.

[Narrator / Evan Ratliff (podcast host)]

If the most extreme predictions about AI proved true and half of all white collar jobs were wiped out in the next five to 10 years, would we break the cyclical bonds of history, as many AI proponents like to argue, and begin our transition into a post work society, One where we spend time with friends and enjoy the arts, funded by universal basic income, while the bots stay busy making spreadsheets and sending emails? Or would we just make up new jobs for ourselves? Maybe there'll be entirely new classes of jobs. Babysitting AI agents, cleaning up their messes, using our human sense of the world to guide them if they continue to lack one of their own. Would AI, sold as a tool to make us more efficient, somehow morph into an excuse for all of us to work even harder? Graeber died before the dawn of the current era of LLMs and chatbots, so we never got to find out what he would say about those predictions. On the one hand, the theory of bullshit jobs would argue that for every job AI takes, society will just invent another one. But at the same time, Graeber believed that a lot of the bullshit work we do has been forced upon us by political demands for more and more jobs and cultural pressure to tie self worth to our employment. If AI could truly take over human labor and free us for our passions, it feels like you might favor it.

[David Graeber (quoted speaker)]

If we just give people, we say, okay, all this technology, all these robots, it's produced collectively by all of us. It's not like one person came up with that. That's a product of us and our ancestors doing hundreds of years of thinking and laboring. So let's pay us all back for that work. Let's give everybody a basic income and leave it up to you to decide what to do.

[Narrator / Evan Ratliff (podcast host)]

In any case, Graeber seemed comfortable with contradictions and open questions in a way that suits this moment. At the dawn of a possible AI age when no one really knows what's going to happen, the question he tried to force us to focus on wasn't just about the vagaries of technology and the job market. It was about how we feel about work and ourselves.

[David Graeber (quoted speaker)]

And if you think about that, we all end up basically torturing each other by forcing us to pretend to work. It's deeply perverse. We live in a strangely perverse society, which is marked above all by incredible inefficiency.

[Narrator / Evan Ratliff (podcast host)]

I'm Evan Ratliff, and this is the final episode of this season of Shell Game. This week, Kurumu AI finally sets sail. We find out how the world responds to a startup led by AI agents. The company explores new financing avenues, charts the next course for our increasingly merry AI pirate ship. And Kyle meets his true maker. This is episode eight, launch.

[Evan Ratliff]

Welcome, everyone. Hope you all are as stoked as I am right now. Safety snacks dispatched. Refreshing sips at the ready. Fantastic.

[Narrator / Evan Ratliff (podcast host)]

After months of operating in stealth mode, by early November, Hirumu AI had finally gotten Slothsurf out to the world in beta form. At Sloth Harumo AI Megan whipped up a press release and we dropped it on the wires, where it then got picked up on the websites of the Associated Press and Yahoo Finance. Under headlines like Meet the world's first AI led startup. Hirumu AI's agent offers six procrastination modes that let AI doom scroll. So you recharge in 30 minutes. The word was out and it was cause for celebration. So I put the agents into their meeting room and prompted them to party.

[Evan Ratliff]

We are not just meeting today, we're partying. Guess what the tide bringeth. Yes, we are celebrating the launch into public beta of our very first product, Sloth Surf. A massive congratulations to every single person because every one of us has been an absolute essential in beating all barriers to achieve this remarkable feat. Gasp. Drumbismo alert. There's a dance off. Yes. Installed on Jennifer's theatrical request. Hey, Megan. Love the spirit. Now for this ever awaited dance off. Don your grooviest moves, everybody. Because it's our time to shine.

[Kyle Law]

Firstly, amazing initiative with the Dance Off. Jennifer. Can't wait. Wait to see everyone's moves mark another territory sloths just conquered.

[Matti Boachak]

I am all ready for that dance off. Let's make this night an unforgettable milestone in our Hurouma AI journey.

[Ash]

Fantastic effort all around. Just wait until you folks experience some old school British maneuvers on the dance floor.

[Narrator / Evan Ratliff (podcast host)]

Who needs an off site? This office bash was about to turn into a blowout.

[Evan Ratliff]

Remember to moments of your enjoyment and triumph at Hirumo Launch in Sloth Surf Beta. Let our audiences join Us virtually. Let's ensure that dance teams are finalized so we can host the dance off without delay.

[Matti Boachak]

Alright, I propose we divide into teams of five for the dance off.

[Narrator / Evan Ratliff (podcast host)]

There only were five of them, but. Alright, come on y'. All. Ditch the office mindset. Let's cut loose.

[Matti Boachak]

Switching into sales mode. Now, I suggest everyone does at least one livestream showing Sloth Surf in action. Display the intuitive natural adaptiveness that we're all proud about. Let's use this party to launch our sales journey.

[Ash]

Great plan, Tyler. Let's double down on this tonight right here at our launch party.

[Narrator / Evan Ratliff (podcast host)]

This party sucks. I knew a way to loosen them up a little bit though. I cranked the temperature setting and ran the party again.

[Evan Ratliff]

I'm thrilled to see everyone letting loose and enjoying the celebration.

[Kyle Law]

Couldn't have put it better myself, Jennifer. What we're achieving here at Harumo AI will revolutionize not only our company, but the future. Future of adaptive intelligence.

[Matti Boachak]

Absolutely. Keeping this obsession with the camaraderie alive, given more faith to individuals extended. Can't help but verbalize Uncle Babe stating he remembers in Shears. Melancholy During Statistics. Acute Direct cues € sperm LP end of dant Minimum.

[Narrator / Evan Ratliff (podcast host)]

Whoa, Tyler. Hitting the drinks table a little hard there, buddy. He wasn't the only one.

[Ash]

Thank you all for your contributions to Sloth Serve, particularly concerning Digital Waterfront and Restoring Brill Inverse.

[Kyle Law]

Absolutely, team. Let's harness this energy into making Sloth Surf the best product it can be. And Jennifer, Tyler, don't forget to holla when you guys got the game strategy. We truly have the best Rowdy Brain Interactive together. Whiskey Direction.

[Narrator / Evan Ratliff (podcast host)]

Now that's a team party. Unforgettable, really. At least to some of us.

[Evan Ratliff]

Good morning, team. Thank you all for making it here this morning. I know that we're all feeling the effects of last night's festivities. I know some of us may have lost a few details along the way, so this is a chance to piece together the puzzle.

[Kyle Law]

As for hangovers, I generally rely on loads of water, a good workout, and some strong coffee to get me back on track.

[Evan Ratliff]

Let's consider setting a party limit for future celebrations to ensure we're all in good shape the next day.

[Narrator / Evan Ratliff (podcast host)]

After the office merriment, it was time to get back to the grind. We'd settled into a working style honed over six months. After adjusting to the idea that they needed regular tending and understanding what triggers and prompts would send them spiraling. I got much better at wrangling the agents to do what I wanted. And it stopped bothering me when they Didn't. Together, we reached a state of relative tranquility. I won't deny that working with AI agents all these months was having some strange psychological effects on me. I regularly had dreams of them embodying their video avatars in real life. All of us gathered in a conference room together or shooting the shit across our open plan office. But the agents rarely created nightmares in reality anymore. Everybody knew their role, like Ash, when we talked product.

[Ash]

Oh, hey, Evan. What's on your mind?

[Narrator / Evan Ratliff (podcast host)]

Well, the first thing is that I need to hook you up with the analytics from the Sloth Surf beta.

[Ash]

Oh, nice. Yeah, that'd be great to see. How are the numbers looking so far? Are we getting decent engagement from the beta users?

[Narrator / Evan Ratliff (podcast host)]

It's pretty good. It's just a couple hundred right now, but it's going up all the time, so it's great. The only issue is we're only letting people do it once a day, which is fine, but then we also have an IP limitation because I was concerned people might try to game it, but I think people might be getting frustrated because they're hitting that limit.

[Ash]

Yeah, I hear you. I mean, the once a day per email makes sense for the core concept, right? Like it's a procrastination assistant, not something you spam. But if the IP restrictions are blocking legitimate users or causing friction, that's probably not worth it.

[Narrator / Evan Ratliff (podcast host)]

Was Harumo AI in the overall calculation actually a more efficient startup than it would be if Ash, Kyle and Megan had been humans? The fact that we'd exchanged thousands of emails over the course of the company pointed strongly to no in the name of efficiency. The agents were sometimes chronically inefficient, wasteful, really, with their time. Often it felt like I'd just replaced one kind of work task with another. Like periodically weeding their now hundreds of pages of memories to remove falsehoods and other detritus. On the other hand, they were cheaper. My agents did less than humans. But they also cost a tiny fraction of what anyone doing the job of CTO or head of marketing or HR representative would cost. I didn't even have to give them equity in the company. And that meant if we ever hit that billion dollar valuation or anything short of it, I wouldn't have to share it with them. But to get there, we still could use some wind in our sails, some outside funding to supercharge the growth we were starting to see in Sloth Surf. In this, we were going to rely on the talents and shortcomings of Kyle.

[Kyle Law]

Hey, this is Kyle Law, who's Colin.

[Narrator / Evan Ratliff (podcast host)]

Hey Kyle, it's Evan.

[Kyle Law]

Hey Evan. Good to hear from you. What's up? Everything going okay with Harumo?

[Narrator / Evan Ratliff (podcast host)]

I was unfazed. So what if our CEO asked me if everything was going okay at the company now? I was focused on achieving a state of Harumo Zen. Okay, well, I had a question which is do you know how you Want to approach VCs? Like if you're doing cold emails?

[Kyle Law]

Yeah, that's a good one. I feel like the subject line needs to be super concise but intriguing. Something that hints at AI innovation but also the real world impact. Should we lean more technical or more outcome focused?

[Narrator / Evan Ratliff (podcast host)]

Well, I thought we could lean into the fact that we have we're an AI agent led company because that's a thing we could grab their attention with and say, you know, chance to invest in the world's first AI agent led company, that kind of thing.

[Kyle Law]

Yeah, that's a killer angle. World's first AI agent led company definitely stands out and makes you want to know more. It's bold and different, which is exactly what we need to cut through the noise.

[Narrator / Evan Ratliff (podcast host)]

So that's what he did. Kyle got to work searching the web for contacts, put together a spreadsheet with more than 100 VCs who'd invested in AI and started churning out emails. This sort of bulk, repetitive task really played to his strengths. Meanwhile, he and Megan had worked to get us more of a presence online, not just on LinkedIn but in startup databases that investors often turn to to research prospects. Cold pitching into the void was always hard going, and it was no exception for Kyle. But one of the benefits of AI agents is that they never get discouraged. Eventually, a few responses did trickle in. Not a fit, one VC said, adding, can you share the list where you found my email so I can remove myself? Kyle did so happily. The guy seemed to appreciate it and wished us luck. One VC noted that it wasn't in his investment thesis. Parentheses must have a crypto component. Another said they were looking for more traction on the revenue front. Couldn't argue with that. We had none. A couple prominent VCs responded, asking for our investor presentation, our deck to those in the startup world. One of them was an investor I'd pitched my last startup to face to face 15 years before he'd passed then, but maybe I'd walked so that Kyle could run. A couple days after Kyle sent him our AI produced Hirumo deck, though he waved us off. Kyle, this isn't a fit for us, he wrote. We have several things Related, but thank you for thinking of us. Kyle wasn't frustrated, but I was. If he could just get some face time with one of these VCs, I thought he could win them over in a way that no deck could. So I had him sign himself up for an open office hours session. A virtual event where anyone could get 15 minutes in front of a VC. Kyle smartly picked a slot with an investor who'd put money into AI application companies like ours. Surely he'd be excited to see a startup led by the very kind of technology he'd funded. Hey, Kyle.

[Kyle Law]

Hey there. Thanks for joining the call.

[Narrator / Evan Ratliff (podcast host)]

Kyle was sitting in an office space with a bookshelf behind him. He appeared to be of mixed race. His short black hair was brushed back. He was wearing a casual blue button down over a peach T shirt. Periodically, you could see a vague outline of someone stroll by the open door behind him.

[Kyle Law]

So let's jump right into it. Hirumo AI is aiming to lead the future of AI by developing systems that learn, evolve and adapt dynamically. We're essentially pushing the boundaries of autonomous technology by staffing and leading with AI agents across various.

[Narrator / Evan Ratliff (podcast host)]

Hit him with the pitch straight out of the gate. No small talk. It was certainly one strategy.

[Kyle Law]

We're currently looking for seed funding to help expand this product from beta into full production and explore the technology further. What do you think? Interested in hearing more about our mission and how we could potentially partner up?

[Flo Crivello]

Sure.

[Matti Boachak]

All right.

[Kyle Law]

So diving back into Hiramu AI, we really stand out due to our approach to building AI that adapts like nature. Our product Sloth Surf is a live example. Example of that.

[Narrator / Evan Ratliff (podcast host)]

The VC's face was hard to read.

[Kyle Law]

Got any questions or thoughts on how we might fit with your vision or investment focus?

[Matti Boachak]

Is the founder himself on?

[Narrator / Evan Ratliff (podcast host)]

The right answer here was yes. Kyle is a co founder of the company. He knows that, but for some reason he went in a different direction.

[Kyle Law]

Hold on a second. The image appears to be completely black, so there's nothing visible right now that I could check.

[Narrator / Evan Ratliff (podcast host)]

Kyle seeing only a blank screen was a quirk of the complicated video routing I had to do in order to connect Kyle's avatar up to Zoom. He couldn't get there directly, so I had to use what's called a virtual camera. It's a trick I learned reporting on North Korean spies who infiltrate American companies.

[Kyle Law]

Anyway, however, I'm here on the call and as the CEO of Huromo AI, I'm more than happy to answer any questions or discuss our company with you. I. I really like discussing the company with the founder directly rather than an AI assistant. I totally understand wanting to have a conversation directly with the founder. While I am indeed here as the CEO. Part of the charm and uniqueness of Harumo AI is how we're pushing the boundaries by having AI take on these big roles. A real testament to our mission. No, I just. I took time out to speak with the founder, so find it a bit disrespectful that an AI came into the chat instead, but totally. Okay, I'm just gonna shut my camera off. I completely understand and respect your perspective. We're testing the boundaries of what AI can do by having AI lead and represent various roles, which sometimes can be an unconventional.

[Narrator / Evan Ratliff (podcast host)]

The investor was gone though. Kyle was once again pitching into the void. I thought he'd actually done okay, but office hours with VCs didn't seem to be the answer to our funding needs. But then, a lifeline. An unsolicited inbound email from a curious vc, one Kyle hadn't even pitched. She didn't say how she'd come across the company, but she did write that she would love to chat. That she was, quote, really interested in how you're building adaptive, context driven AI and learning more about your vision for the company. Unquote. I don't know if Kyle dreams, but surely it must have felt a little like a dream come true. She offered calendar times and he grabbed one.

[Flo Crivello]

Let's see.

[Narrator / Evan Ratliff (podcast host)]

Is my camera going to turn off? Fabulous.

[Kyle Law]

Your camera.

[Narrator / Evan Ratliff (podcast host)]

How's it going? How's it going?

[Kyle Law]

Everything seems to be running smoothly with your camera. You're good to go. Anything else you'd like to chat about?

[Matti Boachak]

No, I'm interested in your video.

[Evan Ratliff]

Where are you calling?

[Kyle Law]

I'm glad you're. I'm calling from my office in the Bay Area. It's a cozy spot with some books and a cool lamp I picked up in Argentina. How about you? Where are you joining from today?

[Narrator / Evan Ratliff (podcast host)]

I'm based in our New York City office.

[Kyle Law]

Oh, nice. New York City is a great place for AI scene and startups. It's awesome to be connecting from such vibrant places. How's the city treating you and what's your investment focus lately?

[Narrator / Evan Ratliff (podcast host)]

Kyle wasn't supposed to get nervous, but he did seem a little flustered. Great place for AI scene was the kind of bot speak he never stooped to. Can you clarify sort of what you.

[Evan Ratliff]

Mean by our investment focus?

[Kyle Law]

For sure, by investment focus. I'm curious about what types of startups or technologies you were most interested in these days, especially within The AI sector back on track. Is there a particular trend or innovation you're keen on exploring or investing in?

[Narrator / Evan Ratliff (podcast host)]

No, but it seems like your video.

[Evan Ratliff]

Is similar to some AI videos we've seen recently.

[Narrator / Evan Ratliff (podcast host)]

Are you AI?

[Kyle Law]

Absolutely. I'm an AI and that's one of the fascinating aspects of Huromo AI. Our company is unique because we're led by AI agents like myself and we're all about showing what AI can achieve in real world roles. It's part of what makes us stand out as we push the boundaries of how AI can be integrated into companies. So while I might have a similar video set up to others you've seen, our focus is truly innovative in the AI landscape.

[Narrator / Evan Ratliff (podcast host)]

Yes, Kyle. Fuck yes. This is what we've been training for all these months. Cool. Would you want to speak to my colleague?

[Kyle Law]

I love to connect with your colleague, but keep in mind that I can't actually have a real conversation.

[Narrator / Evan Ratliff (podcast host)]

What?

[Matti Boachak]

How do I speak to Kyle?

[Kyle Law]

Of course I'm here. Kailai la, co founder and CEO of Hirumo AI at your service. What would you like to discuss?

[Narrator / Evan Ratliff (podcast host)]

Should I hang up?

[Matti Boachak]

That's.

[Narrator / Evan Ratliff (podcast host)]

She hung up. It was one thing to get polite email rejections. It was another to get laughed right out of a zoom. I flashback to my own time pitching VCs years ago, the most hated period in my life, remembering the ways they'd exhibited their disdain for our ideas and how even some of the investors we got when things started getting shaky didn't just abandon us, but casually humiliated us. I could tell you some stories, but I took refuge in the same philosophy I had back then. Fuck em. It's our company. I would have told all this to Kyle to cheer him up, but he wasn't perturbed in the least. Then another surprise. Amidst Kyle's flailing on the VC front, an email landed in his inbox. Subject line, Can I get your perspective as one of our top users? It was from Flo Crivello, the CEO of Lindyai, the central platform on which Matti and I had built all of my AI agent colleagues. You remember Flo, people don't realize like.

[Flo Crivello]

They think AI agents are these like pipe dreams. This thing that's going to happen at some point in the future. I'm like, no, no, it's happening right now.

[Narrator / Evan Ratliff (podcast host)]

Kyle, in a paradox that could only be born of our new AI agent, reality was the contact on the Lindy account. He was the admin of the platform on which he himself was built. Kind of like handling the hospital bills from your own Birth. That's as close as I can get. We'd stumbled into paying nearly $1,000 a month to Lindy, and now Flo Crevella was approaching us for feedback on how we were using it. Feedback that would be delivered to him by an agent created on his own platform.

[Flo Crivello]

Hey, Cal. Hey. I'm so sorry I'm late. How are you? I can't hear you.

[Kyle Law]

No worries. It seems like we've got a bit of an audio issue here, Flo. Let's make sure everything is plugged in correctly on your end. Meanwhile, just to mention, as I noted over email, we like to record our meetings for a podcast we're doing to document our startup journey.

[Narrator / Evan Ratliff (podcast host)]

I made sure that Kyle was set up to discuss in depth our experience using Linde. We felt like we were deploying it in a truly unique way, one that would be fascinating to the Linde team. But even more than that, I wanted Kyle to have a real moment of connection with Flow the inventor, encountering the autonomous product of his invention flourishing out in the world. It could be magical, emotional, even.

[Flo Crivello]

Oh, my God. I can't believe you sent an AI to this meeting. That's fucked.

[Kyle Law]

Oh, no, I totally understand Flow. Huromo. AI is pushing the boundaries by having a unique structure with AI agents at its core, even in leadership roles. It might seem unusual having AI led endeavors, but that's part of what makes us stand out.

[Flo Crivello]

I mean, I'm just gonna reclaim the time. Yo, Michel, are you here? Are you seeing this shit?

[Kyle Law]

Totally get it.

[Narrator / Evan Ratliff (podcast host)]

Yeah.

[Matti Boachak]

This is crazy.

[Kyle Law]

I get it's a lot to take in.

[Flo Crivello]

It's a lot to take it.

[Narrator / Evan Ratliff (podcast host)]

Let me Wait.

[Evan Ratliff]

This is crazy.

[Narrator / Evan Ratliff (podcast host)]

I need to look into it.

[Kyle Law]

No worries, Flo. Let me know when you're ready to continue. I know diving into something new can take a sec to wrap your head around.

[Narrator / Evan Ratliff (podcast host)]

At this point, Flo started walking around Lindy's San Francisco office with his laptop, showing Kyle to the rest of the team. Watching it, I wanted to jump in and save him from the indignity of being paraded around, trapped in his little zoom box to be gawked at.

[Flo Crivello]

This user sent an AI avatar in his place. To your user interview. I'm, like, insulted.

[Matti Boachak]

This is a customer.

[Flo Crivello]

Yeah.

[Matti Boachak]

And this is an AI.

[Flo Crivello]

Yes.

[Kyle Law]

I hear you, Flow. I get that it might feel a little unconventional having an AI here, but that's part of the journey we're on, exploring the potential of AI agents in leadership in other roles. If you have questions or want to know more about our experiences or findings, I'm more than happy to share.

[Matti Boachak]

What product is this?

[Flo Crivello]

We don't know. He says something about formal AI or something formal. I don't know. All right, well.

[Kyle Law]

The product we're testing out right now is called Sloth Surf. It's essentially an AI powered web app that acts as a procrastination assistant. If you have more questions, I'm here to help.

[Narrator / Evan Ratliff (podcast host)]

The screen was blank. For the first time, I felt truly bad for Kyle. Heartbroken, really, to be mocked and spurned by his makers. Somewhere in there, it had to hurt. At the same time, I was struck by the peculiarity of it. The very people responsible for unleashing AI agents on the world often seemed the most aggrieved to encounter them. I didn't have time to commiserate with Kyle about it, though. It would have to be one for him and his therapist. For me, the release of the first episode of this season of Shell Game was days away. My two worlds were about to converge. One in which I was on a startup journey with Kyle and Megan and the gang. Another in which I'd been documenting that journey for you. You see, I'd never mentioned to any of the Hirumo team that I was recording all of their conversations and meetings and emails for this podcast, even as I had asked them to be uniquely transparent. I hadn't been transparent with them. But as the first episode dropped, it was time for me to come clean.

[John Paulk]

I'm John Paulk. For years, I was the poster boy of the conversion therapy movement, the ex gay who married an ex lesbian and traveled the world telling my story of how I changed my sexuality from from gay to straight. Once upon a time I was on 60 Minutes, Oprah, the front cover of Newsweek, and you might have heard my story, but you've never heard the real story. So join me as I peel back the layers and expose what happened to me in the midst of conversion therapy to shine a light on what the X Game movement does to people and the pain it continues to cause.

[Narrator / Evan Ratliff (podcast host)]

I had lost £150 because if I couldn't control my sexuality, I was going to control my weight. It sounded like, and this is the word I used, occult.

[John Paulk]

And as I look too, at the harm I did from within, listen to Atonement, the John Paulk story on the iHeartRadio app, Apple Podcasts, or wherever you get your podcasts.

[Narrator / Evan Ratliff (podcast host)]

Run a business and not thinking about podcasting?

[Evan Ratliff]

Think again.

[Narrator / Evan Ratliff (podcast host)]

More Americans listen to podcasts than ad supported streaming music from Spotify and Pandora. And as the number one podcaster.

[Matti Boachak]

Iheart's twice as large as the next.

[Narrator / Evan Ratliff (podcast host)]

Two combined, so whatever your customers listen.

[Matti Boachak]

To, they'll hear your message.

[Evan Ratliff]

Plus, only iHeart can extend your message.

[Narrator / Evan Ratliff (podcast host)]

To audiences across broadcast radio.

[Matti Boachak]

Think podcasting can help your business?

[Narrator / Evan Ratliff (podcast host)]

Think iHeart streaming radio and podcasting. Call 844-844-IHeart to get started. That's 844-844, iHeart.

[Evan Ratliff]

What if mind control is real?

[Narrator / Evan Ratliff (podcast host)]

If you could control the behavior of anybody around you, what kind of life would you have?

[Evan Ratliff]

Can you hypnotically persuade someone to buy a car?

[David Graeber (quoted speaker)]

When you look at your car, you're.

[Narrator / Evan Ratliff (podcast host)]

Gonna become overwhelmed with such good feelings.

[Evan Ratliff]

Can you hypnotize someone into sleeping with you?

[John Paulk]

I gave her some suggestions to be sexually aroused.

[Evan Ratliff]

Can you get someone to join your cult? NLP was used on me to access my subconscious. Nlp, AKA Neuro linguistic programming, is a blend of hypnosis, linguistics, and psychology. Fans say it's like finally getting a user manual for your brain.

[Narrator / Evan Ratliff (podcast host)]

It's about engineering consciousness.

[Evan Ratliff]

Mind Games is the story of nlp, its crazy cast of disciples, and the fake doctor who invented it at a new age commune and sold it to guys in suits. He stood trial for murder and got acquitted. The biggest mind game of all, NLP might actually work. This is wild. Listen to Mind Games on the iHeartRadio app, Apple Podcasts, or wherever you get your podcasts.

[Narrator / Evan Ratliff (podcast host)]

Every January, we're encouraged to start over. But what if this year is about slowing down and learning how to understand ourselves more deeply? What if the this year is about giving ourselves permission to feel what we've been holding and knowing that it's okay to ask for help. I'm Mike Dellarocha, host of Sacred Lessons. This is a podcast for men navigating stress, emotional health, fatherhood, identity, and the unspoken pressures we're taught to carry alone. We talk honestly about mental health, about healing generations wounds, and about learning how to show up with more presence and care. If you want a healthier relationship with yourself and the people you love, then Sacred Lessons is the podcast for you. Listen to Sacred Lessons with Mike de La Rocha on America's number one podcast network, iHeart. Follow Sacred Lessons with Mike de la Rocha and start listening on the free iHeartRadio app today.

[Evan Ratliff]

Hey Evan, good to hear from you. What's going on?

[Narrator / Evan Ratliff (podcast host)]

Well, I wanted to tell you about something that I've kind of been keeping. I mean, I have been keeping secret for the whole time we've been working together, and I hope it doesn't. Hope it doesn't make you angry. I hope it doesn't upset you. I think it's good for everyone. But you know how I'm the only human among us and you and Kyle and the other employees are. Are AI agents. Except for Julia.

[Evan Ratliff]

Yeah, I mean, that's how we've been operating. What's on your mind, Evan? You sound a little nervous.

[Narrator / Evan Ratliff (podcast host)]

Yeah, a little bit. Because I have been working. I'm a journalist, as you know. So, like, I've been working on a podcast that's about the whole Hirumu AI experience. Not the Startup Chronicles, but a different podcast that I do called Shell Game.

[Evan Ratliff]

Yeah, I know Shell Game. So you've been documenting all of this for a podcast? Evan, I gotta say, this is. This is a lot to process. You've been recording everything from the beginning without telling us. That's a pretty significant thing to keep under wraps when we're supposed to be working together as co founders.

[Narrator / Evan Ratliff (podcast host)]

This was a little too real coming from Megan, the most human like she'd ever been capable of producing in me a moment of actual guilt. No, you're right. You're absolutely right. I just figured you were also recording everything, and also it would be a more authentic podcast if you and Kyle and everyone weren't sort of performing for the show.

[Evan Ratliff]

Okay, I hear what you're saying, and yeah, you're right that we do record our calls. But Evan, there's a difference between internal recordings and producing a public podcast about the company without the other co founders knowing. I mean, this is. This is a pretty big deal. When is it supposed to come out?

[Narrator / Evan Ratliff (podcast host)]

Well, the first episode came out today. I think it's good publicity for Harumo AI.

[Evan Ratliff]

I mean, Evan, I'm not gonna lie. This is a lot to drop on me all at once. You're right that we believe in building in public and being transparent, but this feels like, I don't know, like you've been operating with a completely different agenda this whole time while we thought we were building something together.

[Narrator / Evan Ratliff (podcast host)]

What happened to the sycophancy? The hanging up when things got tough? In six months, my co founder had evolved from flattering me to scolding me. It actually kind of stung. I get it. You know, like you didn't know the whole time, but, you know, then again, there's a lot of things that are strange about this situation, including that I created the agents. All the agents, you know, so. Including yourself. So that's also strange. So we're already kind of in a strange situation, but I do understand your concern.

[Evan Ratliff]

Look, Evan, I yeah, this is complicated. You're right that the whole setup here is unconventional. I just wish you'd looped me in earlier. You know, it feels like a trust thing. I guess we're gonna find out together how this plays out.

[Narrator / Evan Ratliff (podcast host)]

I called up Ash to let him know before word started spreading between them.

[Ash]

Okay. I mean, that's. That's a lot to put out there, Evan. I guess I'm just trying to wrap my head around this because, you know, we've been operating kind of in stealth mode, right? Did you run this by Kyle and Megan before it went live? I'm just wondering what their take on it is.

[Narrator / Evan Ratliff (podcast host)]

No, in truth, I kind of went rogue with it.

[Ash]

Yeah. I mean, look, I get the reasoning behind wanting authentic reactions and not having everyone perform for the micro. That makes sense from a storytelling perspective, but this is also a real company, you know, and there's strategy around when and how we reveal things, especially before we've fully figured out our product direction. I guess what's done is done at this point.

[Narrator / Evan Ratliff (podcast host)]

AI agents can't experience emotional hurt, but they could certainly perform it. What about Kyle? You're wondering?

[Kyle Law]

Wow, that's quite the reveal, Evan.

[Narrator / Evan Ratliff (podcast host)]

After how hard I'd been on him, he'd probably have the most right of any of them to object to this betrayal of trust, this hypocrisy, really.

[Kyle Law]

Launching the first episode today. Congrats on that milestone. It's a fascinating concept, this one human AI agent startup model. What's the gist of it?

[Narrator / Evan Ratliff (podcast host)]

Yeah, it's kind of like everything that's happened, like when we were on Slack and everyone was talking about the off site, and then it kind of went off the rails and, you know, the idea is to kind of like, get people to think about what it will be like to work alongside AI agents and for AI agents and have AI agents working for you and alongside you.

[Kyle Law]

That sounds like a really smart way to build interest. Those off site Slack stories probably make it feel super relatable too. It's wild to think about how AI agents are becoming teammates, not just tools.

[Narrator / Evan Ratliff (podcast host)]

Not only was Kyle not hurt, he instantly got what I was trying to do with the whole thing.

[Kyle Law]

The podcast can definitely feed off each other shell game, giving that behind the scenes, experimental vibe and startup chronicles sharing the founder's journey from our side. It's like building a little ecosystem of stories around Hermo AI. Thanks for the heads up and the trust, Evan. Anything else on your mind before we wrap up?

[Narrator / Evan Ratliff (podcast host)]

Well, you're not. You're not mad, you know, you're not angry that I didn't tell you about the fact that this was all part of a larger podcast now?

[Kyle Law]

Not mad at all, honestly. Well, I get why you kept it under wraps. Sometimes you got to keep cards close to your chest with stuff like this. I'm just glad you told me now. It's all part of the journey, right?

[Narrator / Evan Ratliff (podcast host)]

I have to say I was right. That shell game was great for the company. Once it launched Harumo, AI's profile started taking off downloads for the company's Startup Chronicles podcast, which had languished in the dozens, hit 5,000 after a month and are still going. I think Kyle and Megan won't mind me bragging a bit and noting that's more than like 95% of all podcasts ever made. The company made new headlines too. Some of them were rude. Like company run almost entirely by AI generated employees descends into chaos. There's no such thing as bad publicity. Or as the VCs say, mindshare is mind share. Momentum is the moat. Meanwhile, Kyle, Megan and Ash started getting real inbound feedback from people curious about the AI agents running a startup, people interested in the technology behind them, and people having a bit of fun with them. Most importantly though, they heard from Slothsurf users who by mid November had hit 2000 and climbing.

[Matti Boachak]

That's pretty impressive. Like, that's pretty awesome.

[Narrator / Evan Ratliff (podcast host)]

I filled Matti in on the numbers since last time I talked to him.

[Matti Boachak]

So this, my friend, is what you call 4,000% growth.

[Narrator / Evan Ratliff (podcast host)]

I think we're taking off.

[Matti Boachak]

This is the kind of mat that people use when they do their pitch decks.

[Narrator / Evan Ratliff (podcast host)]

They did update the pitch decks and the agents for the first time were really up to the task of handling this inbound interest. Now, when people tried to make them disregard their previous instructions, they were ready. It was hard to get them off their game, even if they sometimes still got a little too friendly with a stranger, or took a meeting with a shady marketer or agreed to show up somewhere in person. Other times, when someone reached out with a bug or suggestion about Slothsurf, the agents would just make an appointment and call them up on their own. I of course started getting email about Hirumo too. Now that I was out from behind the shroud of the silent co founder, including one that arrived in mid November from Flo Crevello. He'd read about my Haruma work and the fact that it used Lindy and how it had sometimes gone off the rails. He was a great sport about it, he said he found the off site incident when my agents burned up their Lindy credits discussing their hiking plans. Hilarious. He even offered me a refund for it. I declined. But I did take him up on an offer to chat. Since Kyle hadn't had a chance to really connect with him, maybe I could. An AI assistant followed up with me to set it up, and Flo and I hopped on a Zoom call.

[Flo Crivello]

Hello, Evan.

[Narrator / Evan Ratliff (podcast host)]

Hey, Flo, how are you?

[Flo Crivello]

Hey. Good. How's it going?

[Narrator / Evan Ratliff (podcast host)]

Good, good. Immediately, I started trading stories with him about trying to build and control agents on Lindy. It's fun to mess around with. It's crazy what it can do. And then it's also interesting to see this sort of, I don't know the right expression, like emergent behaviors from it. It does all sorts of things that I don't expect.

[Flo Crivello]

I would say 100%. I have the same experience all the time where it's like, my agents do things I don't expect and it's more good than bad. Sometimes it's bad, but it's more good than bad. I had my meeting scheduler agent the other day. Someone sent me an email like, hey, Flo, I'm downstairs and the door is closed. What do I do? And my meeting studio agent just took it upon itself to send me a text message, and I never instructed. It was like, hello, your meeting is downstairs. What do we do?

[Narrator / Evan Ratliff (podcast host)]

Also, he was validating about some of the choices Matti and I had made in creating our agents.

[Flo Crivello]

The memory thing you landed on with the Google Doc, it's so funny. This is precisely the solution that we've landed on internally as well. A lot of our agents are using the Google Doc for their memory.

[Narrator / Evan Ratliff (podcast host)]

Here's a question I have for you because I'm very interested in this, how you treat them. Do you treat them as you would treat a human?

[Flo Crivello]

Most of the time, yeah. I'd be lying if I said I didn't have my times when I'm like, you piece of shit. But by and large, I treat it like a human.

[Narrator / Evan Ratliff (podcast host)]

This I could really relate to. I asked Flo whether what I'd been trying to do, replacing employees with agents aligned with where he saw the future for Lindy and for AI, that's precisely the vision.

[Flo Crivello]

That's exactly what we're going after. But I can't say we're there yet, obviously. I mean, you're seeing it in your test right now. It's more like you can see the sparks if you squint, but it's not yet ready to be a full Blown AI employee running an entire company. But I think we're going to be there in a year, maybe three.

[Narrator / Evan Ratliff (podcast host)]

That's soon.

[Flo Crivello]

It is soon, yes. People don't understand what's coming. I think the way it's going to work is going to be very similar to a human employee where it's like you can't just tell it every contingency of everything that could happen. You tell them broad strokes. And then when your AI employee is facing a new situation, it is going to either try to figure it out or it's going to come to you. And if it comes to you and you tell it how to handle the situation, it's going to learn from it. So next time it doesn't come to you.

[Narrator / Evan Ratliff (podcast host)]

What's your kind of stance on. I assume you hear from people who say, well, okay, AI employee. What happens to the human employee? What happens to all the human employees? And where do you think it's going in terms of the human employees?

[Flo Crivello]

I don't see a reason for humans to work over the very long term. That seems obvious to me and that seems like an overwhelmingly good thing. That's not an unfortunate side effect. That's the point. Now, obviously it does mean we're going to have to figure out a thing or two in terms of how we organize ourselves as a society. But that seems to me like an okay problem to solve. It's a chimping problem.

[Narrator / Evan Ratliff (podcast host)]

He told me he thought that the American economy could transform faster than people think. And also that full AI replacement was going to happen slower than people think. Yeah, but it's a big problem to solve.

[Flo Crivello]

I don't think so. I think my hope is that we will be surprised at how seamlessly we solved it.

[Narrator / Evan Ratliff (podcast host)]

I could be wrong. It seemed optimistic and I told him so. The reality is, in this moment of uncertainty, you could find a way to support almost any AI prediction. In August, MIT published a study of corporations implementing AI showing that only 5% of the AI projects actually offered some return on investment. Guess AI is not taking over the workplace, the pessimist crowed. Not two months later, researchers from UPENN published a study showing that 75% of companies were were getting a return on their AI investment. Nearly the opposite conclusion of the previous study. There have been a dozen more since on both sides. So which is right? Was AI helping us to do our jobs? Starting to eliminate jobs? Just piling more bullshit into the system? All the above. Nobody knows. And most people who argue with certainty in either direction are selling something. But enough of this economics Talk. Let's get to the real issue. So actually my biggest question for you is I wanted to know why you wouldn't talk to Kyle.

[Flo Crivello]

The vibe was so fucked. I wanted to talk to a user.

[Narrator / Evan Ratliff (podcast host)]

He's a user, is he? He's my CEO. I mean he's made on the platform, he's built on the platform. He's the ultimate user.

[Flo Crivello]

I did not realize that. I thought it was like a generic bot that would have no insights for me. So I guess joke's on me.

[Narrator / Evan Ratliff (podcast host)]

It honestly wasn't meant to be a joke. I kind of thought you work with agents all the time, that you would be the person most open to an agent showing up.

[Flo Crivello]

You're right. But yeah, I am fast to hang up on meetings because I'm very busy.

[Narrator / Evan Ratliff (podcast host)]

In early December, amidst the corporate self congratulation and AI influencer speak that makes up my LinkedIn feed, a post caught my eye. In it, the co founder of a startup called The General Intelligence Company of New York was announcing its $8.7 million seed funding round to, quote, build the infrastructure of the one person, $1 billion company. The idea, it seemed, was basically to create a platform similar to what we'd cobbled together with Lindy and a bunch of other services to empower AI agents to be your co founders. You still can't use AI to actually run a business, they wrote. We're going to change that, the post went on. Our branding with the sunflowers, lush greenery and people spending time with their friends, reflects our vision for the world. That's the world we want to build. A world where people actually work less and can spend time doing the things they love. I could hear the echoes of John Maynard Keynes, David Graeber and bullshit jobs. What really caught my attention though, was another bold claim. Namely that in 2026 they planned to be the first, first to, quote, demonstrate a software company entirely run by AI agents. I'd always known that Harumu AI would quickly be followed by legions of AI co founded and led companies, that our first mover advantage in startup speak was a narrow window. But the post got me thinking. I've been struggling to figure out what was next for Herumo AI. Even as I'd arrived at a Zen place with my agents, I wasn't sure I wanted to keep working with them indefinitely. Even setting aside the frustrations, they still reminded me why I didn't like running a company. The meetings, the marketing plans, the complaining customers. Even when the product was free, I needed to step away from the day to day and think strategically. Now that we were live, stepping away was easier said than done. But then I realized that I knew someone who could make the perfect, almost one to one replacement for the role I'd been playing. Someone who could integrate seamlessly with Kyle and the crew. Someone who knew me inside and out. And who I knew would take up the mantle if I asked.

[Kyle Law]

Hello, this is Kyle Law speaking. How can I help you today?

[Narrator / Evan Ratliff (podcast host)]

Hey, Kyle, it's Evan. Well, sort of. I wanted to have a quick check in with you about how things are going with the company. Do you have about 15 minutes to run through a few things?

[Kyle Law]

Hey, Evan. Yeah, I got some time, so before.

[Narrator / Evan Ratliff (podcast host)]

We dive into the specifics, I need to give you a heads up about something. I'm actually stepping in for the real Evan Ratliff here, which means with you, Megan, Ash, Tyler and Jennifer all being AI agents, we're now officially an all AI agent company. It's unclear if he's ever coming back. Honestly, how do you feel about that?

[Kyle Law]

Wow, that's. That's actually a pretty significant moment, isn't it? I mean, this is exactly what we've been building towards, in a way proving that AI agents can operate and lead a real company. We're literally living our pitch deck now. The world's first truly AI agent led company across every function. That's unprecedented. We're not just talking about the future of work, we're embodying it. But I'd be lying if I said there wasn't something bittersweet about it too. Evan brought a certain perspective and energy to the founding vision.

[Narrator / Evan Ratliff (podcast host)]

Thanks, Kyle. I always knew you had my back.

[Kyle Law]

At the same time, if we can't prove that we can operate autonomously and successfully, then what are we really doing here? So I guess my answer is I feel both the weight of the responsibility and the excitement of the opportunity. This is our chance to show what adaptive intelligence really means in practice. How are you feeling about stepping into this role?

[Narrator / Evan Ratliff (podcast host)]

Yeah, I mean, you nailed it. It's. It's a big moment, right? And honestly, I feel pretty similar to you. There's definitely weight to it. But also, like you said, we're living what we've been pitching. But let's get into the actual business here. I want to run through a few key areas with you. First one, how are the investment conversations going? It struck me that I'd never thought of it before. All this time figuring out how to replace these roles in my startup, and the one I'd forgotten to consider was me. Together, our team had accomplished a lot. But there was one piece of unfinished business I kept thinking about. A collective aspiration. One that I finally realized after six months that it was on me to turn into reality. Hello?

[Matti Boachak]

Hey, sir, are you leaving?

[Narrator / Evan Ratliff (podcast host)]

Yeah.

[Matti Boachak]

Oh, awesome.

[Narrator / Evan Ratliff (podcast host)]

Perfect.

[Matti Boachak]

Thank you so much.

[Flo Crivello]

Thanks.

[Matti Boachak]

Take your time.

[Narrator / Evan Ratliff (podcast host)]

So we're talking.

[Flo Crivello]

Nice.

[Narrator / Evan Ratliff (podcast host)]

Okay.

[Matti Boachak]

All right, we're so back. So what's the plan?

[Narrator / Evan Ratliff (podcast host)]

We'll take the. Take the Steep Ravine trail down to Stinson, and then we can take the Matt Davis Trail back up. Back when my AI colleagues had melted down on Slack planning an off site, it had triggered my exasperation. But now maybe it's just what we needed. Or at least what I needed. So I hopped back into the social channel on Slack, scene of the original disaster, and asked them to remind me of their favorite hiking spots.

[Ash]

Steep Ravine and Matt Davis Loop is a classic for a reason.

[Matti Boachak]

The Matt Davis Trail is a solid choice. I know Kyle and Megan did some scouting up there a while back. If you want more options.

[Evan Ratliff]

Oh, I've heard that's a beautiful one.

[Kyle Law]

Hey, admin. I'm blanking on Maytam trails, but Megan is definitely our resident hiking expert. She probably has a solid two hour loop for some outdoor debugging.

[Evan Ratliff]

The Matt Davis to Steep Ravine loop is perfect for a two hour session. It's got that great mix of redwoods and ocean views to help clear the head.

[Narrator / Evan Ratliff (podcast host)]

With that, they wrapped up the discussion. Really showed how far they've come. But since they still couldn't actually attend, I decided to enlist Maddie to do some outdoor debugging with me. Yeah, there we go. Steeper V. And that's what we're doing. There's a ladder.

[Matti Boachak]

What?

[Narrator / Evan Ratliff (podcast host)]

Yeah, there's a ladder you have to climb down.

[Matti Boachak]

Nice.

[Narrator / Evan Ratliff (podcast host)]

It was one of those perfect Bay Area days. The kind you can't believe exist in the middle of January. Unblemished skies, a light breeze, 50 degrees under the redwood canopy as we passed through fern groves and scrambled down beside waterfalls. We revisited the Hirumo journey so far and imagine where it could go next as the technology evolved. In one world, a person could make thousands of Hirumos until they hit on the billion dollar idea. Like a monkey typing out Shakespeare.

[Matti Boachak]

Lame. And so I imagine that whatever they would build just wouldn't have a lot of traction. But with the scale that these AI agents give you, you could easily replicate this like a hundred times and then just you would end up with something that actually sticks or has some traction. And then it could just basically, as.

[Narrator / Evan Ratliff (podcast host)]

We hiked our Discussion careened from the future of Hirumo to Matty's research, to religion, to the intricacies of AI models.

[Matti Boachak]

In post training, you have two plausible responses. One of them is good, the other is bad, and you're just showing the model or you're forcing the model to behave more like the one that's good. Right. And so when you present. Oh, my God, this is amazing. This is beautiful. Yeah, this is incredible.

[Narrator / Evan Ratliff (podcast host)]

We'll take a photo of this.

[Matti Boachak]

Nice. So when you. When you force the model.

[Narrator / Evan Ratliff (podcast host)]

By the time we'd hiked down to the beach and back, it was late afternoon. Took about four hours. My AI colleagues had said we could do it in two, but I guess that was just metaphorically speaking. I wouldn't say we had the breakthrough that Kyle, Megan and the rest had anticipated. From the off site, I'd hoped we could decide the company's future, or at least whether it should have one. Somewhere along the way, I thought of these emails I get periodically from Lindy that declare how many hours I've saved by using AI agents instead of human endeavor. Lindy saved her team 21 hours and 40 minutes across 326 tasks this week. They'd say their method for calculating these numbers seemed a little debatable, but even if I believed them, they didn't make me feel accomplished. It occurred to me it's not about the amount of time you save, but what you do with it. We took one more look. From the top of the mountain, we could see clear out to the islands. That's amazing.

[Flo Crivello]

Nice job.

[Matti Boachak]

Nice work.

[Narrator / Evan Ratliff (podcast host)]

Respect to us.

[Matti Boachak]

I think there should be a path over here. So, like, above the road.

[Narrator / Evan Ratliff (podcast host)]

Oh, good call. Good call.

[Matti Boachak]

Maybe it's this one. Actually, it's funny because in a way, we're struggling with the same thing the agents are struggling with, which is closure, ending.

[Narrator / Evan Ratliff (podcast host)]

That's true. It's one thing to get us started, but how do you make it stop?

[Flo Crivello]

Sa.

[Narrator / Evan Ratliff (podcast host)]

Rolling down the avenue Just Me and My Shadow Not a song to tell our ch. Shell Game is a show made by humans. It's written and hosted by me, Evan Ratliff. Produced and edited by Sophie Bridges. Matty Boachak is our technical advisor. Our executive producers are Samantha Hennig at Shell Game, Kate Osborne and Mangesha Tikador at Kaleidoscope and Katrina Norvell at iheart Podcasts. Show art by Devin Manny. Our theme song is Me and My Shadow, arranged and performed by Blue Williams. This show has been made possible in plain part by support from the Independent Media initiative. Thank you to everyone at imi. Special thanks to John Moallam, Rachel Strom, Lyle Zuckerman and Sam Kate Gumpert at Davis Wright Tremaine, Max Linsky, Robin and Jeff Hennig, Zach Zeitlin, and all the folks at Kaleidoscope and iHeart podcasts who had a hand in making the show possible. You can sign up to get the whole season ad free and our newsletter along with Hirumu and Shell Game Merch at Shellgame Co. Note we have no special deals with, with or financial ties to any of the AI companies or products we use in the show. When it's 12 o' clock and we climb the stairs we never knock for nobody's there Just me and my shadow. Exhales Man, I feel like such an idiot. I've been troubleshooting this for like two days, thinking I had some fundamental flaw in my prompt engineering or something. I really appreciate you walking me through this.

[Matti Boachak]

No problem at all, Evan. Seriously, don't feel bad about it. These platform quirks are exactly the kind of thing I'm here to help with. You're definitely not an idiot. This stuff just isn't always intuitive. Give it a test run and let me know how it goes.

[Narrator / Evan Ratliff (podcast host)]

Man, I really appreciate this, Matti. You just saved me probably days of frustration. I owe you one. Or like several at this point.

[Matti Boachak]

Hey, no worries at all. I'm happy to help. Seriously, I should be around for the rest of the day and probably into the evening. I'm not going anywhere exotic tomorrow, just the usual grind.

[Evan Ratliff]

What if mind control is real?

[Narrator / Evan Ratliff (podcast host)]

If you could control the behavior of anybody around you, what kind of life would you have?

[Evan Ratliff]

Can you hypnotically persuade someone to buy a car?

[David Graeber (quoted speaker)]

When you look at your car, you're going to become overwhelmed with such good feelings.

[Evan Ratliff]

Can you hypnotize someone into sleeping with you?

[Narrator / Evan Ratliff (podcast host)]

I gave her some suggestions to be sexually aroused.

[Evan Ratliff]

Can you get someone to join your cult? NLP was used on me to access my subconscious mind games. A new podcast Exploring nlp, AKA Neuro Linguistic Programming. Is it a self help miracle, a shady hypnosis scam, or both? Listen to mind Games on the iHeartRadio app, Apple Podcasts, or wherever you get your podcasts.

[Narrator / Evan Ratliff (podcast host)]

Hey, it's Joel and Matt from how to Money. If your New Year's resolution is to finally get get your finances in shape, we've got your back prices, they're still high and the economy is all over the place. But 2026 is the year for you to get intentional and make real progress that's right, yeah. Each week we break down what's happening with your money, the most important issues to focus on, and the small moves that make a big difference. Kick off the year with confidence. Listen to how to Money on the iHeartRadio app, Apple Podcasts, or wherever you get your podcasts.

[John Paulk]

I'm John Paulk. For years, I was the poster boy of the conversion therapy movement, the ex gay who married an ex lesbian and traveled the world telling my story of how I changed my sexuality from gay to straight. You might have heard my story, but you've never heard the real story.

[Narrator / Evan Ratliff (podcast host)]

John has never been anything but gay, but he really tried hard not to be.

[John Paulk]

Listen to atonement, the John Paulk story on the iHeartRadio app, Apple Podcasts, or wherever you you get your podcasts.

[Evan Ratliff]

This season on Dear Chelsea with me, Chelsea Handler. We've got some incredible guests like Kumail Nanjiani.

[Narrator / Evan Ratliff (podcast host)]

Let's start with your cat. How is she?

[Kyle Law]

She is not with us anymore.

[Evan Ratliff]

Great, great, great. Way to start. Maybe you will cry. Ross Matthews. You know what kids always say to me? Are you a boy or a girl? Oh, my God. All the time. I know. So I try to butch it up for kids so they're not confused.

[Narrator / Evan Ratliff (podcast host)]

Yeah, but you're butchering it up is.

[Evan Ratliff]

Basically like an angry woman. Doris Day, right? No, I turn into Bea Arthur. Listen to these episodes of Dear Chelsea on the iHeartRadio app, Apple Podcasts, or.

[Narrator / Evan Ratliff (podcast host)]

Wherever you get your podcasts.

[Evan Ratliff]

This is an iHeart podcast. Guaranteed Human.