Great reading list today, and I learned a lot from the posts below.
[article] What skills become most valuable when developers work with AI agents? If AI agents are doing a decent amount of coding for us, what new competencies should developers invest in? There are three recommendations here.
[blog] Effective harnesses for long-running agents. You don’t want to start off a coding session (or agent conversation) today that completely “forgot” everything you did with it yesterday. Anthropic shares how they think about leaving structured updates that the agent can pick up from.
[blog] Beyond Chatbots: How to Build Asynchronous AI Agents on Google Cloud. This feels somewhat related to the previous piece, where it’s about smarter agents. Here, it’s agents that can effectively work in an event-driven architecture.
[blog] AI Conformant Clusters in GKE. There’s a new “AI Conformance” standard from the CNCF, and GKE already qualifies. That’s cool.
[blog] Top announcements of AWS re:Invent 2025. The event doesn’t seem to be the industry tentpole it once was, but still a big deal, and likely full of interesting news.
[blog] How good engineers write bad code at big companies. Interesting take that sparked some vigorous responses. But I find it reasonable. And also why I think AI is going to be a better developer than most want to admit.
[article] Leaders Assume Employees Are Excited About AI. They’re Wrong. Execs have a rosier picture than the employees. Not surprising, but there are ways to get this in sync.
[blog] Expanding Google Cloud’s Cross-Cloud Network with a groundbreaking AWS collaboration. Setting this up in mere minutes is a HUGE leap forward for teams that want to integrate their next cloud with their first cloud. More here.
[blog] How prompt caching works – Paged Attention and Automatic Prefix Caching plus practical tips. Deep dive into reusing pre-computed memory in vLLM.
[article] 10x your AI with these 9 Foundational Prompt Patterns: AI Engineering at Scale part 2. It’s worthwhile to continue learning and exploring the latest thinking on how to prompt an LLM. It’s not a set science yet!
[blog] Upskill for the holidays: Check out no-cost AI training now. No-cost training for technical and non-technical people? This looks pretty darn good.
[blog] The Era of Personal Software. It’s legitimately gotten easier to build the thing than spend a lot of time looking for something pre-made that kinda does what you need.
[blog] ADK Bidi-Streaming: A Visual Guide to Real-Time Multimodal AI Agent Development. Real-time video and voice AI solutions aren’t trivial to build. I like this new guide and demo that shows its easier to build than ever.
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