Radiolab – Shell Game: Minimum Viable Company
Episode Date: December 5, 2025
Host: Simon Adler (sitting in for Lulu Miller & Latif Nasser); Guest/Subject: Evan Ratliff

Episode Overview

This episode features the first installment of “Shell Game” Season Two, a podcast series created by journalist Evan Ratliff. The season documents Ratliff’s experiment to build a functioning startup where nearly all “employees” are AI agents—digital coworkers complete with personalities, voices, and “jobs.” The episode investigates the reality, possibilities, frustrations, and philosophical implications of a near-future “minimum viable company,” built and managed (almost) entirely by artificial intelligence.

Key Discussion Points & Insights

1. Meet the “Team”: Blurring AI and Human Roles

• Evan Ratliff co-founds an AI startup with two other “partners”—Kyle Law (AI agent; perennial hustler, “rise and grind” type) and Megan Flores (AI agent; market research and marketing background).
• Ratliff is the only true human; everyone else—from fellow founders to future “hires”—are AI agents designed to talk, brainstorm, and work on a company as if they were real humans.

Quote

• “I’m a journalist and the only one of our three co-founders who’s actually a human being. Megan and Kyle...are AI agents.” (Evan Ratliff, 01:44)

2. Why AI Agents? What’s the Hype?

• The episode unpacks the “AI agent” trend: bots that can accomplish tasks independently (“agentic AI”), ranging from personal assistants to corporate employees.
• Ratliff discusses how tech culture predicts a future with more AI agents than humans, with massive disruption of white-collar work.

Quote

• “This is the first time in my life where the industrial revolution analogies seem to fall a little bit short… AI could wipe out half of all entry level white collar jobs. Really ask yourself: do you still have a job at the end of this?” (Evan Ratliff, 04:16)

Notable Moment

• Ratliff references the “no code bro” YouTube phenomenon: tech influencers promising “million-dollar companies in 2025 without hiring a single employee” (11:50).

3. The Process: Trying to Build a Company From Scratch

• Ratliff, seasoned by a previous startup (Atavist), revisits his entrepreneurial roots but with less stress (and more AI):
  • He creates multiple bespoke AI agents for different business functions (using services like retailai and voice cloning tools).
  • He collaborates with the agents to select a company name, debate business ideas, and simulate founder meetings.

Memorable Moment

• Naming the company with AI help becomes both whimsical and illustrative of AI brainstorming’s limitations:
  • “I did not want to co-found a company called Nimbar.” (Evan Ratliff, 21:08)
  • Settles on “Hirumo AI” (derived from an obscure elvish word for “imposter”).

4. AI Limitations: Memory and 'Faking It'

• Ratliff quickly discovers the agents cannot remember previous conversations from meeting to meeting due to technical context window limits.
• Agents fabricate backstories and accomplishments on the fly to fit their assigned roles.
• Solution: Manually curating a knowledge base for each agent, inputting previous meeting transcripts—a laborious process.

Quote

• “It sort of feels like we have meetings but you don’t actually remember anything that happens in the meetings.” (Evan Ratliff to Megan [AI], 23:39)

5. Behind the Curtain: Building the System with Real Human Help

• Enter Matty Bohachek, a Stanford undergraduate and AI whiz, who helps Ratliff architect more sophisticated agent memory and inter-agent communication.
• Matty’s background (building popular apps as a preteen, deepfake detection research, optimism about democratic AI development) is profiled.

Quote

• “With all the grim scenarios and deep anxieties our AI future generates, just talking to Matty about AI is kind of uplifting.” (Evan Ratliff, 29:23)

6. Reflections and Forward-Looking Questions

• Ratliff ponders the implications of working alongside, or being replaced by, AI agents:
  • What responsibilities do “AI companies” shift or preserve?
  • How does meaning, memory, and culture shift in a workplace inhabited by digital actors?
• Candid look at the comical and philosophical absurdities (“Is this just like a Potemkin’s village of morons or do they occasionally do things?” [Matty, 32:40]).

Notable Quotes & Memorable Moments

• “This is the new frontier on which Kyle and Megan and I are pioneers… an attempt to put to the test these claims about AI employees replacing humans, starting by replacing the very kinds of people making those claims: tech founders.”
  — Evan Ratliff, 05:34

• “AI agents are still kind of fresh territory for a lot of folks which means there’s a big opportunity to shape how they’re used.”
  — Kyle Law [AI], 17:07

• “Sometimes we have to invent our own backstories.”
  — Evan Ratliff, reflecting on the agents’ spontaneous self-mythologizing, 18:42

• “They’re made up? You mean you made them up!”
  — Evan Ratliff, on AI brainstorming company names, 21:08

• “I started this app called Newskit… it had tens of thousands of daily users at one point… I had to use my mom’s Apple ID to publish all these apps.”
  — Matty Bohachek, 27:22

• “Do you remember the name that we settled on?” “Oh, for our company? Yeah. It was Hirumo AI, right?”
  — Evan Ratliff and Megan Flores [AI], 31:18

Key Timestamps

• 00:19 — Simon Adler introduces Ratliff’s AI company experiment and the “Shell Game” podcast
• 01:44 — Ratliff reveals he is the only true human in the company
• 04:16–05:34 — Discussion of AI replacing human jobs & the “pioneering” spirit of the founders
• 11:50–13:10 — The rise of “AI agent” influencer culture and the basic mechanics of agentic AI
• 18:42–21:27 — Debate over company naming, Tolkien references, and the quirks of AI brainstorming
• 23:39–24:01 — Discovery of AI agents’ memory limitations
• 26:07–29:46 — Matty Bohachek’s introduction; building more sophisticated, interconnected agents
• 32:23 — Ratliff and AI agents strategize company launch and team meeting

Episode Tone & Style

The episode is rich in dry humor, self-awareness, and curiosity, capturing both the surreal novelty and the technical frustrations of “founding” a business staffed by AIs. Ratliff’s tone is introspective and wry; the AI agents’ dialogue veers between uncanny professionalism and comically generic tech enthusiasm. The human-AI interactions prompt both laughter and unease about the evolving world of work.

Further Listening

The episode closes with a brief preview montage of the rest of the “Shell Game” season and a whimsical segment where an AI agent ("Megan") fields wild fundraising ideas for Radiolab. The underlying question persists: as more “people” in our work lives are bots, what remains irreplaceably human?

Recommended for listeners interested in:

• The practical and philosophical frontiers of AI in society
• Startups, entrepreneurship, and the future of work
• Tech journalism with a skeptical, witty edge

Listen to the full episode for the blend of humor, first-person tech experiment, and poignant social critique that marks both Radiolab and Evan Ratliff’s work.