Following last week’s intense focus on tokens, it’s interesting to see some folks (https://x.com/mvanhorn/status/2063865685558903149) doubling-down on token-intense practices such as loop engineering. While others, in today’s reading list, explore the important human role in AI work.

[blog] Do better research with NotebookLM (https://blog.google/innovation-and-ai/products/notebooklm/better-research-notebooklm/). Sweet update. Better models, more types of output formats (e.g. PDF, Excel, Markdown), and more help getting started on research.

[blog] How I Actually Code (and Review) With AI in 2026 (https://medium.com/google-cloud/how-i-actually-code-and-review-with-ai-in-2026-005c89fbd113). Thoughtful post, and actionable too. Steal some of these prompts/skills for your coding harness.

[blog] Using Agent Platform Memory Bank and Sessions from other runtimes (https://wdenniss.com/using-agent-platform-memory-bank-and-sessions-from-other-runtimes). Services that support agents (like those providing memory) need to be available to any runtime, not tightly coupled to one.

[article] Embedding pipelines are the new ETL (https://www.infoworld.com/article/4181232/embedding-pipelines-are-the-new-etl.html). When you do ingestion, chunking, and indexing for your embedding pipeline, are you doing the equivalent of extract-transform-load exercises?

[blog] What’s worth learning in an AI era? (https://davenporter.substack.com/p/whats-worth-learning-in-an-ai-era) “Do I need to learn this” is a profound question to ask yourself right now. And how deep do we need to go?

[youtube-video] Software engineering at the tipping point (https://www.youtube.com/watch?v=2n41YjR5QfU). Wow, watch this. Seriously. Important talk for the AI era and why engineering matters more than ever.

[blog] Choosing Values for Robust Tests (https://testing.googleblog.com/2026/06/choosing-values-for-robust-tests.html). Quick simple advice for us to follow if we want to avoid false confidence in our test suite.

[blog] How to Secure AI Agents: A Practical Overview for Development Teams (https://www.docker.com/blog/how-to-secure-ai-agents/). Check this out to see which four security domains Docker thinks you should pay attention to when delivering agents.

[blog] Is Valkey Ready to Replace Redis in 2026? (https://devops-daily.com/posts/is-valkey-ready-to-replace-redis-2026) Not a definitive “yes” nor a definitive “no.” This piece has a few useful considerations to factor in.

[blog] Coding Is No Longer the Constraint: Scaling Developer Experience to Teams and Agents at Spotify (https://engineering.atspotify.com/2026/6/code-with-claude-coding-is-no-longer-the-constraint). Use fewer things, but be great at the tech you invest in. That’s Spotify’s engineering vibe, and it’s serving them well.

[blog] Deploying Hermes AI Agent and WebUI on GCP: A Step-by-Step Hands-On Guide (https://medium.com/google-cloud/deploying-hermes-ai-agent-and-webui-on-gcp-a-step-by-step-hands-on-guide-ee32303c4bfb). If you’ve got the tokens and personal agents like crave loops, run stuff like Hermes and OpenClaw.

[paper] Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering (https://arxiv.org/abs/2601.14470). Source paper for an article I shared a month or so ago. It’s more timely right now as people suffer under the weight of rapidly-consumed token budgets.

[article] The AI Agents Stack (2026 Edition) (https://www.oreilly.com/radar/the-ai-agents-stack-2026-edition/). Nice job. It’s a good look at various layers and components that make up modern agents.

Want to get this update sent to you every day? Subscribe to my RSS feed (https://seroter.com/feed/) or subscribe via email below:

					Subscribe (https://seroter.com/?post_type=post&p=30191)