Daily Reading List – November 3, 2026 (#902)

Today was a leadership summit for Google Cloud people. We learned a lot, and got fresh appreciation for the scale of engineering we do here.

[article] AI agents don’t have to break security controls to go rogue. Here’s how to keep them in check. Containment failure (breaking out of a sandbox) is different from authority failure (using available capabilities to do more than supposed to). Good distinction here.

[blog] Monday Morning SDK Maintenance with Antigravity Scheduled Automations. Moving past chatbot interactions is an important step in actually changing the work. Scheduled automations and async workers are the leap forward.

[blog] Predictions 2027: AI Turns Up The Heat On Software Development. These make sense to me. Are you preparing yourself individually, and your team for this rapidly-approaching future state?

[blog] How to run coding agents in parallel without piling up PRs. I liked the advice here. Not everything should be done in parallel. And what is, needs definitions of done, isolation, and smart task boundaries.

[blog] Building a LiteLLM Enterprise Gateway for Antigravity. This is new functionality, and pretty cool. Add an intermediary gateway if you want to introduce custom model routing, cost attribution, and auth flows for your AI coders.

[article] OpenAI built itself a new Git backend, too. Everybody’s building their own git backend? Nah. But we’ll keep seeing changes here that flow into the big shared software services. OpenAI post here.

[blog] Google Cloud Developer plugin now available in Antigravity Marketplace. This was smartly designed, and has already gotten fairly popular. Consider following some of the patterns we call out here.

[blog] The AI Manager Is the Easy Part. Trusting the Code Is the Hard Part. Some thoughts here on building autonomous engineering teams.

[blog] How we scale deployments with a custom GitOps engine. IaC and GitOps aren’t dead. But they’re continuously changing. Here’s a post from LinkedIn.

[article] In one of the largest deals in tech history, Marvell buys Lumentum for $115B. Not super familiar with either, but clearly there’s a big bet on AI and data centers.

[article] Are AI certifications still worth it? What changed in 2026. Good question, with some answers here. I’m not sure you should get certified to improving your job prospects; use them to prove to yourself that you’ve learned something.

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

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.