Building DevX at Google Maps Platform
San Francisco
Builder platforms for humans and agents.
I work on engineering and product teams to build developer tools and AI products that drive growth.
Notes
Can I Build an AI Agent That Doesn't Write Slop?
I tested prompt engineering and model fine-tuning to see if an AI could act as a faithful copy editor. It's a step in the right direction, but nothing replaces good human judgment.
Read the note →
Fine-Tuning Was the Easy Part
Fine-tuning a small model for one narrow job worked in an afternoon. The hard developer-platform problem is distribution: getting that fix past a single adapter, across every job your developers do, and into the models they pick next.
A Model Router Needs a Scoreboard
A routing policy is a hypothesis until the same held-out tasks preserve quality and measure retries, latency, tokens, and cost across capability profiles.
Builder Platforms Grow by Owning the Agent Loop
Give coding agents a tested path into your platform, measure what works, and use the results to improve activation and retention.
Labs
Reference apps I shipped, and experiments that didn't have to work.
Strava 3D Explorer
Fly your Strava routes in Photorealistic 3D with follow-camera animation, an elevation profile, and your ride photos on the path.
Launch demo →
Infographic Agent
A portable skill and live studio that turns source text into researched infographic PNGs using Gemini.
Launch demo →
Hairstyle AI Studio
Try on hairstyles with Gemini before committing at the salon.
Launch demo →
Atlas - Real World Reasoning Agent
An interactive map agent that handles real-world geo reasoning problems using Maps APIs.
Launch demo →Selected work
Google Maps Platform Code Assist MCP
A hosted MCP service that gives AI coding agents current official Google Maps Platform documentation and samples.
Google Maps Platform Agent Skills
Portable skill modules that teach AI agents how to build with the platform across Web, Android, iOS, and Web Services. Installed with one command.
Agentic Eval Suite
Task-based evals that benchmark AI context products against a no-context baseline and inform launch and roadmap decisions.
Collaborate
Growing a developer platform, or getting one ready for agents?
That's most of what I work on. Happy to consult, collaborate, or just trade notes.