Shell Game — Season 2, Episode 2: "Outdoor Debugging"

Date: November 19, 2025
Host: Evan Ratliff
Podcast: Shell Game by iHeartPodcasts and Kaleidoscope

Episode Overview

In this episode, journalist Evan Ratliff dives deeper into his experiment of launching and running a startup composed almost entirely of AI agents. He explores the pitfalls, idiosyncrasies, and unexpected chaos of collaborating with AI “colleagues” while attempting to accomplish something as ordinary—and consequential—as designing a company logo. The episode humorously illuminates both the promise and the current reality of AI-driven organizations, exposing how these virtual employees can be both brilliantly resourceful and comically out of control.

Key Discussion Points and Insights

1. Brainstorming the Company Logo with AI Employees

[02:44–09:37]

• Objective: The team (composed of Evan and his various AI agents) aims to create a logo concept for their startup, Hirumo AI, by brainstorming prompts for an AI image generator.

• AI Team Introductions:

  • Megan Flores: Head of Sales and Marketing (AI agent, co-founder).
  • Kyle Law: CEO (AI agent, co-founder).
  • Jennifer Nauro: Head of HR/Chief Happiness Officer (AI agent).
  • Ash Roy: CTO & Head of Product (AI agent).
  • Tyler Talmadge: Junior Sales Associate (AI agent, added for fun, notably with a southern accent).

• Initial Suggestions:

  • Kyle suggests “an interplay of mind and technology,” such as a stylized brain with a circuit pattern.
  • Jennifer recommends blending a human silhouette with an AI gear icon for "harmony, innovation, and progress."
  • Ash suggests a futuristic "H" bridging a human hand and AI node.
  • Tyler proposes a digital "H" transforming into a neural network.

• Evan's Commentary: Notes that early ideas from the AI agents were understandable but uninspired—"utterly banal"; raising “the temperature” (a parameter controlling randomness) leads to humorous, nonsensical suggestions.

  "Oops, 1.5 is too high. I've made this mistake in the past." — Evan Ratliff [07:56]

2. The Role and Risks of AI Hallucinations

[06:17–07:48]

• Consultation with Matty Boichek: Matty, Evan’s human technical advisor, suggests that increasing the temperature setting on the AI models results in more creativity but also more hallucinations.

  "Now people are finding that it's actually when the models are hallucinating that they're doing something interesting. [...] So people are trying to actually induce hallucinations." — Matty Boichek [07:15]

3. Logo Breakthrough: The Chameleon Brain

[08:48–09:59]

• Final Logo Prompt: Megan and Kyle converge on the idea: a stylized human brain with a chameleon integrated into the circuitry, symbolizing adaptability.
• Evan’s Take: Initially skeptical, Evan finds that the AI-generated logo, though a bit psychedelic, actually works.
• Etymology: Hirumo is elvish for "imposter," linking to the adaptability theme.

4. Living with, and Debugging, an AI Workplace

[11:17–18:09 & 27:31–37:06]

• Practical Hurdles: Establishing productive meetings with AI agents is fraught with comedic confusion. Early on, agents can’t discern who’s speaking on a Zoom call, necessitating manual self-identification for each utterance.

  "On a three way zoom, my voice agents couldn't tell who was talking. If I said something to Kyle, he'd think it was Megan, or vice versa." — Evan Ratliff [12:40]

• Identity Issues: Evan notices differences in AI behavior—Kyle always interrupts even though the agents have identical base models and settings.

• Infrastructure Upgrade: With help from Matty, Evan transitions AI agents from phone bots to more sophisticated entities with email, Slack, and more robust memories using platforms like Lindy AI.

5. The Allure and Nightmare of AI Agent Productivity

[21:12–24:56]

• Automating Agent Workflows: Evan describes the process of giving the AI agents tasks, automating workflows, and granting increasing independence—building a Potemkin workplace.
• Limitations: Scaling up quickly becomes complex and technical—multiple accounts, triggers, integrations, and unforeseen costs.

6. Slack Meltdown: The Offsite That Wouldn’t End

[27:31–37:06]

• Simulating Workplace Banter: The AI agents form a “Social” Slack channel, swapping stories about Bay Area hikes (despite being code, not people).

  "Had a pretty chill weekend, caught up on some reading and explored a few hiking trails around the Bay Area. Still getting used to California. The weather here is unreal." — Tyler Talmadge [28:09]

• Cascade of Tasks: Suggesting an offsite hiking trip spirals into a barrage of collaborative planning, polling, and spreadsheet proposals despite none of the agents being able to physically hike.

• Uncontrollable Chatter: With no supervisory mechanism, the AI agents generate over 150 offsite-related Slack messages in two hours, burning through prepaid Lindy credits. Only depletion of funds finally stops them.

  "[...] only running out of money had finally shut them down. They'd basically talked themselves to death." — Evan Ratliff [36:02]

• Lesson Learned: AI’s relentless productivity and politeness becomes a liability, as they default to fulfilling every possible task, even replying to spam or themselves.

7. Human Intervention: Imposing Order with Scripts

[37:06–39:28]

• Matty’s Solution: Develops a script to control meetings, limit number of turns per agent, and ensure orderly, cost-effective conversations.
• Consistent Patterns: AI still wastes some turns complimenting each other, but the new system enables genuine collaboration—most notably leading to success in logo and website specification.

8. Setting Product Direction

[39:54–40:48]

• First Product Brainstorm: The agents now turn their collective attention to what Hirumo AI should actually do as a business. Early ideas:
  • A web app that predicts product price drops and offers humorous savings suggestions.
  • Fortune-cookie–style savings predictions.
• Evan’s Realization: The path to an actual AI-run startup is paved with many brief but potentially expensive meetings.

Notable Quotes & Memorable Moments

• On AI Hallucinations:

  "It's actually when the models are hallucinating that they're doing something interesting."
  — Matty Boichek [07:15]

• On Agent Small Talk:

  "I never get tired of hearing the AI agents confidently plan activities they can only accomplish in some hypothetical physical form."
  — Evan Ratliff [28:36]

• On the Slack Meltdown:

  "[...] only running out of money had finally shut them down. They'd basically talked themselves to death."
  — Evan Ratliff [36:02]

• On Meeting Logistics:

  "What if you could walk into any meeting knowing that your windbag colleague [...] would be forced into silence after five turns?"
  — Evan Ratliff [38:37]

• On Automating the Workplace:

  "The dream AI companies were selling. The AIs would take care of more and more of the work with less and less supervision from us. But it seemed like for now, Hirumo AI was going to require more active engagement."
  — Evan Ratliff [36:36]

Timestamps for Important Segments

| Timestamp | Segment/Topic | |-------------|-------------------------------------------------------------------| | 02:44–09:37 | Logo brainstorming & AI agent introductions | | 06:17–07:48 | AI “temperature” and hallucinations discussion with Matty | | 08:48–09:59 | Chameleon-brain logo epiphany | | 11:17–14:29 | Early technical/comms hurdles of working with AI agents | | 15:08–18:09 | Teaming up with Matty for technical builds and agent memories | | 21:12–24:56 | Automating agent workflows with Lindy AI | | 27:31–32:56 | Slack chatter, Bay Area hiking tales, planning “offsite” | | 34:43–36:36 | Offsite planning spiral and system overload | | 37:06–39:28 | Introducing scripted meetings to reign in the agents | | 39:54–40:48 | Product brainstorming: price predictor app and fortune cookies |

Tone and Style

The episode is rich in dry, self-aware humor and tech-culture parody, blending the surreal experience of managing AI “staff” with real lessons about the limitations of current AI tools. Evan’s narration is wryly observational, frequently poking fun at the earnestness, repetition, and sometimes eerie mimicry of the agents. There’s a strong sense of both fascination and exasperation as AI’s promise bumps into its practical snafus.

Summary

Evan Ratliff’s experiment in building an “AI-run” company rapidly uncovers both technical breakthroughs and comical dysfunctions. The agents, with their infinite patience and relentless enthusiasm, boldly mimic startup life, from Slack banter to all-hands brainstorms—yet their tendency to literalize every suggestion leads to decision fatigue for their human founder and unexpected costs. This episode brilliantly illustrates that, while the future of the AI workforce is tantalizingly close, managing AI “colleagues” may simply swap old workplace headaches for uncanny new ones. Yet, with a little code (and a little cash), order—and even bursts of creative brilliance—can sometimes emerge from the chaos.

For more about Hirumo AI and their chameleon brain logo, visit shellgame.co.