This was a blur of a week, and I try to avoid those. I usually do a better job of truly breaking it up to slow down the key parts. Not this week. But, it’s a good-looking weekend ahead, and unintuitively, Google I/O will likely be more low-key than “regular” work.
[blog] Unlock software delivery excellence and quality with Gemini Code Assist agents. Good look at why improving the coding experience alone isn’t enough to improve software delivery performance. It may actually have the opposite effect!
[article] Renovate to Innovate: Fundamentals of Transforming Legacy Architecture. Learn from Rashmi about the what, when, and how of technical renovations of legacy systems.
[blog] Ollama’s new engine for multimodal models. Ollama is the engine of choice for many folks that want to run LLMs locally. Now, with multimodal support.
[blog] Getting AI to write good SQL: Text-to-SQL techniques explained. Very interesting post about the hard parts of getting AI-generated SQL, and the architecture we’ve built.
[blog] Building software on top of Large Language Models. Simon built some lands-on labs for a workshop on building apps that use LLMs. He’s using the wrong model, but nobody’s perfect. Still, great assets.
[docs] Generative AI glossary. A lot of terms get thrown around nowadays. We just published this new glossary of generative AI terms and I like the depth we provided for each one.
[blog] Exploring Agent2Agent (A2A) Protocol with Purchasing Concierge Use Case on Cloud Run. Distributed agents, working together? That’s what this blog post shows.
[article] Building Custom Tooling with LLMs. Nice example of taking something and extending it using tools built with an LLM.
[article] Thousands of people have embarked on a virtual road trip via Google Street View. What a useless and awesome thing. I watched it today for a few minutes.
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