Agentic Checkout
Google · 0→1 → Google I/O · Webby 2026 Best AI Agent
Agentic Checkout ("Buy for Me") is an AI agent that completes multi-step purchase workflows end to end. I took it from a 0→1 idea to its public debut at Google I/O; it was recognized with the 2026 Webby Award for Best AI Agent.
How it started
The idea came first, from my own pain point: the thing I wanted would drop in price — and I still had to watch it and buy it myself. I imagined the product that should exist: an agent that completes the purchase you've already decided to make. My first direction didn't survive contact with real merchant constraints, so I killed it and went back to where user intent is most explicit — upgrading the existing price-tracking product. It could tell millions of shoppers when to buy, but carried them no further.
A hackathon as the lever
A cross-team idea rarely survives the normal process. So I took it to an internal hackathon instead: assembled a small team across browser and UX, compressed the vision into a demo that ran and a story that landed — and won first place. The prize wasn't the point. It bought leadership attention, and the AI infrastructure team came to us asking to collaborate.
Aligning three orgs behind one blueprint
Between a winning demo and a real product sits the work demos never show: evaluating build-vs-reuse paths (existing checkout infrastructure vs browser-automation web agents — the latter won), designing the system architecture, and running the cross-team workshop that fixed the MVP scope — turning scattered conversations into actionable docs and priorities. Shopping, payments, and AI ended up aligned behind one blueprint.
The make-or-break: reliability
Checkout is adversarial and high-stakes — an agent that usually works is a demo, not a product. Through systematic agent design, prompt iteration, and eval pipelines, checkout success went from roughly one-in-four to production-grade on target flows. That number is what turned demos into an official product track — and it's where I learned the lesson that shapes all my work since: an agent is only as good as the system that verifies it.
Recognition
Shipped at Google I/O; recognized with the 2026 Webby Award for Best AI Agent.