Staff Engineer · Airbnb
Agentic AI on the systems businesses run on.
I'm a staff engineer with fifteen years on enterprise platforms. These days I build agentic AI on top of the systems businesses run on, and I write about what it takes to make it reliable — the guardrails, the human-in-the-loop, and the engineering around the model.
Featured — selected writing
02 pieces
Your Agents Open PRs Faster Than You Can Review Them
When a few agents are opening pull requests all day, review becomes the bottleneck. The strategies teams ahead of this are using — automate the mechanical, AI first-pass review, stacked PRs, humans on intent, verification upstream — how well they work, and how to set them up.
I Write Far Less Code Than I Used To. The Job Got Harder.
The metaphor went from autocomplete to agent, and the engineer's job went with it — from writing code to directing and checking the things that write it. What actually changed, why the productivity isn't automatic, and the skill that matters now.
Latest — most recent
All posts →Loop Engineering: What It Actually Means, and How to Do It Right
"Loop engineering" is getting thrown around as the next big buzzword after prompt engineering and context engineering. Underneath the hype there's a real design problem: the plan-act-verify-decide cycle that makes an agent either grind through real work or spin in place. What each stage of that cycle actually needs.
Harness Engineering: The Layer That Actually Decides Whether Your Agent Works
Same model, wildly different reliability, depending on what's built around it. What harness engineering actually means, the layers a production harness needs, and an implementation-level look at the three real ways to build one — Claude Agent SDK, OpenAI Agents SDK, and rolling your own with LangGraph or a raw tool loop.
Loops, Not Prompts: How Codex and Claude Code Finish Real Work Unattended
A prompt gets you one round trip: ask, answer, done. A loop keeps going until a real stopping condition fires. How Codex CLI's /goal and Claude Code's /loop actually work, and the contract that makes it safe to walk away from either one.
Why a 95% Reliable Step Does Not Make a 95% Reliable Agent
Every step in your agent workflow tests fine in isolation, and the whole thing still fails more than you'd expect. The reason is multiplicative, not mysterious — and once you see the math, it changes how you design the workflow.
Your Agents Open PRs Faster Than You Can Review Them
When a few agents are opening pull requests all day, review becomes the bottleneck. The strategies teams ahead of this are using — automate the mechanical, AI first-pass review, stacked PRs, humans on intent, verification upstream — how well they work, and how to set them up.