Accelerating LLM-Driven Developer Productivity at Zoox

"You open the docs, and it feels like reading a novel. You bounce between Confluence, GitHub, Slack, random PDFs, trying to reverse engineer how anything works. Back then, if you had a question, you had two options, read more docs, or even worse, ask another human. Terrifying times. It was normal. We all just powered through it. Fast forward to today, developers expect AI everywhere: AI in their editor, AI in Slack, in all the tools. When AI is missing, it feels broken."

"This talk is about that shift, not hype, not magic, but a systematic approach through the entire developer lifecycle. My team focuses on one question, how do we make developers productive using LLMs? Everything you see today is from real production work, real wins, and a healthy number of mistakes. Roadmap: start by looking at the developer lifecycle as it exists in a complex enterprise, then talk about the platform built to address constraints, then applications for different workflows, and finally how adoption was driven."

"Let us zoom in on what a new developer actually goes through. It never starts with writing code, it starts with information discovery. They spend days, sometimes weeks, trying to piece together how things work. Are there any docs? Where do the docs live? That phase alone can burn the first month. Then, there is personal productivity. What are the internal tools available? How do internal tools work? Which dashboards matter? Who are the subject matter experts?"

A new developer begins with information discovery, locating documentation and understanding where knowledge lives, often spending days or weeks before writing code. After discovery comes personal productivity, including learning internal tools, dashboards, and identifying subject matter experts. The lifecycle then moves into collaboration and execution, where developers need fast answers, consistent guidance, and reliable workflows across systems. Developers increasingly expect AI in their editor and communication tools, and missing AI feels like a broken experience. A platform and set of applications were built using real production work to improve developer productivity with LLMs, including a focus on adoption beyond building the tools.

Read at InfoQ