Today’s guest is Amelia Wattenberger, former principal research engineer at GitHub and now Partner at Sutter Hill Ventures.
But she’s also a Product Lead at Augment Code, where she developed Intent, a developer workspace for orchestrating AI coding agents and delivering complex work. So this is a fascinating chat into the future and the present of software development with someone who has clearly been at the very frontier of this for many years.
If you like the podcast, please give us a rating on your platform of choice! It means a lot to us — that’s how other people discover the show! ⭐⭐⭐⭐⭐
🥇 Interview Summary
If you are a 🔒 paid subscriber 🔒 you will find my own summary of the interview below.
It’s the 5-minute takeaways of what we talked about, with timestamps to the relevant video moments, for those who don’t have time to sit through the 1-hour chat.
Here is the agenda for today:
🧩 What is Intent and why rethink the IDE
🤖 Orchestrating agents and smart defaults
📋 The living spec as a control plane
🚀 How AI multiplies (or doesn’t) different engineers
🔮 The changing shape of roles and specialization
⠀Let’s dive in 👇
1) 🧩 What is Intent and why rethink the IDE
The IDE has been around for nearly half a century, and every single pixel in it is devoted to reading and understanding code. But as AI agents get better at the nitty-gritty of code comprehension, Amelia argues our role as developers is shifting toward higher levels of abstraction — and our tools haven’t caught up.
Intent is Augment Code’s take on what comes after the IDE. Its core primitive is the workspace: for any piece of work, you spin up an isolated environment that bundles a copy of your codebase (with its own branch and Git worktree), a set of agents, rich markdown notes, terminals, and a spec. You can run multiple workspaces at once, switching between tasks without the mental overhead of juggling Git branches or remembering scattered chat conversations.
“Every single pixel in the IDE is devoted to reading and understanding code. And it feels like as agents get better at the nitty-gritty, our role as developers has changed, where we’re working more at higher levels of abstraction, where we have more leverage.”
Amelia describes how we’ve essentially “hacked” AI into existing primitives — chat in the IDE, chat on the command line, chat on GitHub — without rethinking what the interface should look like when developers spend more time on intent and planning rather than writing individual lines of code. Intent is an exploration of that question.
2) 🤖 Orchestrating agents and smart defaults
One of Intent’s most opinionated design choices is how it handles agent orchestration. By default, the app ships with specialist personas — a coordinator that delegates to implementers and verifiers — but everything is tweakable through natural language settings.
Amelia explains why splitting agents into focused roles works better:
