Now I’m in Boston getting ready to keynote a conference tomorrow. Check out some good items below on modern developer tooling, voice Ai apps, and how to think about software development.
[article] The best IDE for agentic AI may not be an IDE at all. Workspace coordination is a problem to solve. If you’ve got a bunch of work happening across tools and agents, how do you manage it all? There’s no set solution yet.
[blog] Build real-time voice applications with Gemini 3.8 Live and 3.5 Transcribe. Forget living in the chat box. Think about how real-time voice apps, with sophisticated tool calling, could change how you (and customers) get things done. More here.
[blog] 3 Highlights from Thomas Kurian’s Keynote at the Goldman Sachs Communicopia & Technology Conference. Nobody’s better at giving you three points than Thomas. He has a compelling pitch in the linked presentation.
[blog] Pair Programming With Your AI Agent. Have you paired before? This post calls out four styles of pair programming, and how to apply each to AI coding sessions.
[blog] Agent-ready analytics: Unlocking insights with BigQuery augmented analytics. We’re so past doing basic queries with AI. Now we’re able to do causation, trend analysis, and so much more. Really cool.
[article] Leaders, Don’t Let Your Jokes Fall Flat. Sigh, I know. Looking at the “science of humor” is weird, but the advice here does make sense. Will I follow it? Nobody knows.
[blog] We are all Product Engineers now. If you want a sober, realistic view of where we are and where we’re going, read this. I didn’t find much to disagree with.
[blog] Agent Permissions in Antigravity. YOLO mode is fine for demos, but even if you trust your agent, you’ll want a more granular and thoughtful approach to agent permissions.
Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below:
Richard Seroter's Architecture Musings 
Leave a comment