Daily Reading List – May 14, 2026 (#784)

Today’s list feels a bit more cynical (pragmatic?) about AI than usual. That’s ok as it’s important to see the full range of perspectives.

[blog] The Road More Traveled. A look back at what the point of microservices was, and the impact of AI on architecture.

[blog] Build Long-running AI agents that pause, resume, and never lose context with ADK. Can your agent run for a week without getting messed up? Here’s a reference system that you can browse and learn from.

[article] Tokenmaxxing is super dumb. Again, I get the reason people do it. I’ve asked my own team to think AI-first, but it doesn’t mean I care how many tokens they consume each day.

[blog] An Engineer’s Guide to Better AI Skills: Implementing a Testing Process to Optimize Agent Performance in Any Repository or Skill.The Pinterest engineering team shares their thoughts on evals and such.

[article] Google Cloud is hiring an army of AI deployment engineers. It’s true. Customers need to own their AI journey, but we’re going to be invested in their success.

[blog] Google Cloud Next 2026 Data Content. Skim through this list and find a talk or two that you’d like to watch.

[article] AI is creating a generation of developers who can’t debug their own code. Can you explain your code? Fix an issue? If you’re hiring juniors who say no to both, you’ll need to change something.

[article] Chamber 🏰 of Tech Secrets #56: Signal in the Noise. Brian pulled out some relatively durable points about AI from a recent in-person event.

[article] Burnout and Cognitive Debt. This doesn’t tread any new ground, but still offers a useful, sobering reminder to consider the human impact of our AI-fueled work.

[blog] Learning Software Architecture. Like most things, software design is best learned through hands-on experience. But this post also points out that an application’s architecture is usually shaped by an org’s incentives and social dynamics.

[blog] Code Review Responses: Add Context When It Counts. The gist of this advice is “say more.”

[blog] MCP vs. CLI: Which Is Better for Agentic AI? Both work well, it just depends on your use case and the environment your agent is running in.

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