Show Notes
What happens when a company stops relying on a shared Notion doc to remember how it works — and lets AI agents do that instead? This week, Gabi is joined by Jean-Denis Greze, co-founder and "Mayor" (not CEO) of Town, an AI assistant startup that just raised a $55M Series A led by Andreessen Horowitz. Before Town, Jean-Denis spent nearly seven years as CTO of Plaid, scaling the engineering org from 20 people to 350 through a $13.4B valuation. He breaks down his thesis of the "self-organizing company," how Town's agents read across email, Slack, and docs without eroding trust between coworkers, and why — despite building an AI assistant for a living — he still won't let his own agent send an email on his behalf. Guest: Jean-Denis Greze, Co-founder & CEO & "Mayor," Town Links: town.com
🎧 Brought to you by Anchor Browser — cloud-native browser infrastructure for AI agents.
More from Agent Hour
Most AI assistants will do anything you ask, and that is exactly why they cannot do anything on their own. Nir, founder of Catch and a former early-stage investor at a Tel Aviv VC firm, drew a frame around his product and told users plainly what sits inside it: calendar, email, travel, and daily operations. Anything else is somebody else's job. On this episode of Agent Hour he explains why that refusal is the whole design. Because Catch only handles admin, it can build a profile of how long you like your meetings, which days you work from home and who your key relationships are, then act before you ask. He walks through the two-key trust model the product runs on, where the agent takes an action unsupervised only when you have granted it and the system's own confidence is high enough, and he describes what happened the night his agent booked over his plans and he refused to reschedule, so the team would feel the cost of the failure themselves. 🎧 Brought to you by Anchor Browser — cloud-native browser infrastructure for AI agents.
Kush Bhuwalka wants to build an agent that starts and runs its own company. First he'd like people to stop running agents on a Mac Mini under a desk. In this episode of Agent Hour, Gabi Weinberg talks with the founder of Puffle AI, an AI teammate working inside Slack, GitHub, Linear and Notion for construction, manufacturing and logistics companies about why always-on machines are the wrong foundation. Keep a box running and every credential, tool and database connection ends up on it, all reachable by the model runtime. Strip those out one by one, as most teams eventually do, and the only thing left is the runtime itself: serverless, arrived at by accident, the same path the web took from rented servers to functions. He's equally direct about the limits autonomous pull requests are "slop," he says, even though Puffle opens them for his own team every day. The difference is whether a human reads one before it ships. 🎧 Brought to you by Anchor Browser — cloud-native browser infrastructure for AI agents.
More than 60% of the traffic hitting Fly.io's properties, and over 70% of the behavior inside the platform itself, is driven by agents rather than humans, and roughly two-thirds of the revenue is now agent-native. Gabi Weinberg talks with Scott Johnston, the new CEO of Fly.io, who was at Netscape for the birth of the commercial web and ran Docker through the container wave, about what those numbers do to an infrastructure company. Fly is seeing single node, single geo, stateful, spiky traffic that has nothing to do with Monday through Friday, and billing per agent per human rather than per application. Scott walks through what Fly built for that, including checkpoint and restore fast enough to roll back a loop that went wrong, and real-time credential injection so an agent can reach its tools without ever holding the keys to them, plus spin-to-zero pricing, the moat question, and whether any of this is a bubble. 🎧 Brought to you by Anchor Browser — cloud-native browser infrastructure for AI agents.
Most browser agents take a screenshot and guess where to click. rtrvr.ai doesn't take screenshots at all. In this episode of Agent Hour, Gabi Weinberg sits down with Arjun Chintapalli and Bhavani Kalisetty, the ex-Google engineers who bootstrapped rtrvr.ai from a Chrome extension into a cloud browser platform and an in-product onboarding agent. Their argument is technical: language models are language models, extraordinary at semantic understanding, mediocre at finding a pixel coordinate. So rather than train a vision model, rtrvr.ai compresses a page's DOM, which can run into millions of tokens, into a representation that preserves every possible action, with element IDs mapped to real on-page text so the agent has far less room to invent things. It also runs on any off-the-shelf model, including text-only ones like DeepSeek; cheap enough, they argue, that a single ad impression could cover an entire agent task. 🎧 Brought to you by Anchor Browser — cloud-native browser infrastructure for AI agents.
Evan Barnard runs AgentGrail, an AI-powered sports and trading card intelligence platform that scans live eBay listings around the clock and calls BUY, PASS, or REVIEW using computer vision and price/grading reasoning trained on thousands of graded slabs. On this episode of Agent Hour, Evan joins to talk about why a niche, high-emotion hobby market turned out to be a great testbed for autonomous agents, what breaks trust when a bot's buy call is wrong and real money's on the line, and what generalizes from trading cards to agentic commerce everywhere else.