My goodness, today was bonkers. A dozen or so meetings, tons of exciting product updates to review offline, and a fire drill in the office. But the opposite is terrible (to me), so the non-stop action is perfectly fine.
[article] Mission, Vision, poTAYto, poTAHto. Really good. We can act like mercenaries who just get our job done, but I do like knowing there is a bigger purpose in mind. Jason provides a more down-to-earth way to arrive at that purpose and vision.
[blog] To get better at technical writing, lower your expectations. I definitely get the point here. You don’t have to be Shakespeare, or include every detail. Help the user quickly get the most relevant information.
[blog] Choosing Your Agent Framework. You can build your own, but there are many cases where a batteries-included agent framework is the right way to go. Allen gives an honest review of the options out there.
[blog] Building for an Open Future – our new partnership with Google Cloud. Hugging Face and Google Cloud are doing more together. Better model download performance, native use of TPUs, and more. Here’s our perspective.
[article] Overcoming the Organizational Barriers to AI Adoption. You can’t just hand your team AI tools and tell them to do better work. It doesn’t matter how good those tools are. Invest in training, frank conversations about roles, and prioritize areas that employees actually care about.
[article] Secrets of Performance Tuning Java on Kubernetes – The Article (Part 2). My friend Bruno looks at a few key configurations to ensure your Java containers scale and perform correctly on Kubernetes.
[blog] How to Build an Offline Agent with ADK, Ollama and SQLite. Great example of building an agent that can function even when the network is down.
[blog] Unleashing autonomous AI agents: Why Kubernetes needs a new standard for agent execution. From our open source team. Every Kubernetes distribution can take advantage of this now.
[blog] The Real AI Bottleneck Is Organizational Reinvention, Not Computing Power. Some very frank talk here from Forrester. I don’t think I disagree with any of it.
[blog] When Good Locks Go Bad: Diagnosing a System Meltdown Under Load. Good story from Flipkart’s engineering team. This is also why you really need to understand. your system architecture and code. Don’t outsource that to AI.
[site] Get inspired by what you can do with Claude. Here’s a very helpful set of use cases for whatever your favorite LLM is.
[blog] NotebookLM adds Deep Research and support for more source types. If your job involves any information collection and research—which tech job does not?—then you should be using NotebookLM.
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