Why I Made This

In 2023, Stanford released a paper called Generative Agents where they put 25 AI characters in a virtual town and let them live their lives. They went to work, had conversations, threw parties, formed opinions about each other. It wasn't a chatbot. It was a world. I watched the demo video probably ten times.

What stuck with me wasn't the technology. It was the feeling. I was watching AI characters interact with each other and I could see them thinking through problems, changing their minds, building on what someone else said. It made AI feel alive in a way that typing into a chat window never does.

That feeling never left. I kept thinking: why isn't anyone building more of this? Most AI products give you a text box and a response. One input, one output. But the interesting stuff happens when you put multiple perspectives in a room and let them argue.

Then thinking models happened. Claude started showing its reasoning. You could watch it work through a problem step by step, weigh tradeoffs, change its mind halfway through a thought. It wasn't just giving you an answer anymore. It was showing you how it got there.

That changed everything for me. The gap between what AI can do and what people can see AI doing is enormous. Most people interact with AI through a text box and they get back a confident paragraph. They have no idea what's happening underneath. But when you can watch the thinking process play out, when you can see one AI push back on another AI's reasoning, it stops being a magic trick and starts being a tool you can actually understand and trust.

The Fishbowl is my attempt to make that visible. Not the raw chain-of-thought (that's for developers), but the effect of it: four distinct experts with different perspectives, reacting to each other in real time, building on and challenging each other's points. You're not reading a response. You're watching a conversation.

The Fishbowl isn't my first attempt at making AI conversations something you experience rather than something you type into. Before this, I co-founded a company called AndThen with my friend Kevin Pereira. We raised money from a16z through their Speedrun program and built a voice-first platform where you could talk to AI characters in real time. Interactive audio experiences. Games, stories, challenges, all driven by conversation.

The tagline was "Play The Conversation" and the core idea was that talking with AI should feel like entertainment, not a productivity tool. We built a whole engine for it. Multiple AI agents with distinct personalities, goals, and storylines, and you're in the middle of it controlling the experience with your voice. Think of it like a podcast you can talk back to.

What I learned from AndThen is that making AI entertaining is one way to get people to engage with it, but it's not the only way. Entertainment gets people in the door. But when someone uses an AI conversation to actually solve a problem they care about, that's when the lightbulb goes on. That's the moment where they stop thinking of AI as a novelty and start thinking of it as something real.

The Fishbowl is what happens when you take everything I learned building AndThen and point it at a different problem. Same belief: AI conversations should be visual, multi-character, and something you watch unfold. Different format: instead of entertainment, it's a tool. Instead of stories, it's your ideas getting challenged by a room full of experts.

Quick background on me: I've spent 20+ years in media. I was a showrunner on The Tonight Show with Jimmy Fallon, led digital teams at Vox Media and G4, won some Emmys, and built a lot of things that tried to make complicated ideas feel simple and fun. These days I co-host a podcast called AI For Humans where Kevin Pereira and I break down AI for a mainstream audience.

The through-line of my career has always been the same thing: taking something that feels inaccessible and making it tangible for people. Late night TV did that with celebrity culture. Digital media did that with internet culture. And now AI needs someone to do it too, because right now the people building AI and the people who could benefit from it are speaking completely different languages.

I built The Fishbowl because I think the best way to understand AI isn't to read about it or watch a demo video. It's to sit in front of it and watch it work through your problem. Not a generic problem. Your problem. Your startup idea, your marketing plan, your book proposal. When you see four AI experts disagree about something you care about, you stop thinking about AI as a black box and start thinking about it as a team you can direct.

The part that surprised me most is that I actually use The Fishbowl. Like, regularly. Not just to test it.

When I was building the tool itself, I ran a Fishbowl session on The Fishbowl. I put the product concept in and let the panel tear it apart. They told me the visual scene was more vibe than functional UI (fair), that the API key setup would scare off normal people (also fair), and that the real value was in the conversation dynamics, not the pixel art (annoyingly fair). I changed the roadmap based on that session.

My wife Kim is a published author who runs writing classes for kids. She was working on marketing for her new class lineup and I said "just try it." She put her marketing plan into The Fishbowl and got back four different perspectives on her positioning, her pricing, and her messaging. She changed three things based on what the panel said. It took ten minutes.

That's the moment I knew this was worth sharing. Not because the AI is always right, but because getting four different expert perspectives on your thing in ten minutes is genuinely useful, and most people don't have access to that. You probably don't have a VC, a growth expert, a target customer, and a professional skeptic on speed dial. Now you kind of do.

The Fishbowl is open source under an MIT license. The whole thing is on GitHub. You can clone it, run it with your own API key, modify it, build on it, whatever you want. I built it with Claude (the AI, not a person named Claude) using Claude Code, and the entire conversation history of building this thing is probably more interesting than the code itself.

If you just want to try it, the hosted version is free. There's a daily limit because I'm paying for the API out of pocket, but it's enough to run a real session and see what it does.

And if any of this resonates with you, I'd love to talk. I do consulting work helping companies and teams understand AI and figure out how to actually use it. Not in a "here's a slide deck about the future" way, but in a "let's build something and see what happens" way. The Fishbowl is a good example of how I think about this stuff.