Daily Reading List – January 29, 2026 (#710)

This morning, I read a blog post about a new product feature (the new conversational analytics baked into BigQuery), tried it out, and included it in a customer demo I did twenty minutes later. Gosh I love managed services that make that scenario possible.

[blog] Vibe coding needs git blame. This is a conversation worth having. I’m not sure I believe (currently) that prompts are merely intentions, not a build input. But none of this seems settled yet and we should keep figuring it out!

[blog] Accelerate GKE cluster autoscaling with faster concurrent node pool auto-creation. Wow, that’s a massive improvement in provisioning speed for Kubernetes clusters.

[blog] The Social Contract That Never Existed. I’m with Tim. Never got this naive, altruistic view of open source. Business models are under stress, not open source.

[blog] Introducing Conversational Analytics in BigQuery. Super cool feature that completely unlocks the ability for anyone to get insights from data.

[blog] Management as AI superpower. Fascinating post from Ethan that reiterates how important communication and management skills are for getting AI (agents) to do good work.

[blog] Project Genie: Experimenting with infinite, interactive worlds. Create, explore, and remix your own worlds. Just amazing. Available to the top tier of Google AI subscribers.

[blog] Flutter on Cloud Run: Full Stack Dart Architecture. There aren’t many languages you use for frontend AND backend, but Dart is one.

[blog] Building Semantic Search into Your AI Agents. Nice. Our MCP Toolbox for Databases now integrates embedding models into the workflow so that you can search using natural language that gets turned into vectors behind the scenes.

[article] Hands On Comparison: Building a Dynamic Web App in VS Code and Google Antigravity with Prompts Only. Solid evaluation, and I like that the author shares the detailed prompts so that anyone can recreate the experiment.

[article] Evals Are NOT All You Need. Evals are important, but there’s more to it. A process is needed to continuously cycle, not one-off checks.

[blog] Create your own AI language coach in 5 minutes. I feel like I’m too old to learn a new language, but maybe this would be a good test of what AI can do for me.

[blog] Software Engineering in 2026: Predictions from Leaders and Practitioners. We’re ending prediction season, but still good to see what a few smart folks have to say.

[blog] Cloud Run AI Agents: The Ultimate Guide to Serverless AI Deployment. It really is an outstanding service for running AI agents of all sorts, written in any language, and with virtually any resource demands.

Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below: