I’m heading to the Del Mar Fairgrounds tomorrow to watch the horse races. Like last year, I’m going to ask Gemini to help me come up with creative, successful bets. For science, that’s all.
[article] The Right Amount of Spec for Agentic Development. Super post that explores when you need more thoughtful specs, and when you can get by with lighter documentation.
[blog] Governed Growth, Part 1: Better Together, Governed Apart. I can’t say I’ve ever seen this talked about. Casey does a wonderful deep dive into governance of model features, and ensuring you’re not accidentally allowing capabilities that introduce unacceptable risk.
[article] Determining the ROI of AI requires data that most companies lack. Do you have the required data sources to piece together the story of actual AI impact? Your AI vendor can’t give them all to you.
[article] Google justifies its massive AI spending with a booming cloud business. Google Cloud is growing like gangbusters, and we still can’t satisfy all the demand. Build, build, build away.
[blog] 5 Software Architecture Mistakes That Make Systems Hard to Change. I don’t think AI agents are going to solve all of these mistakes. They’ll make them too without the right direction from you.
[blog] Introducing Claude Opus 5. It’s got some Fable-like performance at half the price. Available wherever models are sold, including your favorite cloud.
[article] The State of AI Impact in Engineering: Q2 2026. Here’s a report based on real user data. It looks like AI code generation is up, quality might be down, and developer experience is declining. All while spend is ahead of outcomes. We’ll see how this changes, quarter to quarter.
[blog] The Rise of the Subagents. I’m glad to see smarter people building on my primitive looks at subagents. Daniela’s “agent swarms” are intriguing.
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