Daily Reading List – March 19, 2026 (#745)

It’s fascinating to watch the evolution of thinking on a new topic. Agent skills are relatively new, and people are figuring out good practices. Should they be high-level or low-level? All inclusive within the Markdown or always distributed into scripts and resources? Anthropic had a good X article this week (https://x.com/trq212/status/2033949937936085378), OpenAI published some insights (https://developers.openai.com/blog/skills-agents-sdk), and Google shipped a useful X article (https://x.com/GoogleCloudTech/status/2033953579824758855). Build things and learn for yourself what makes sense to you.

[blog] Production Is Where the Rigor Goes (https://www.honeycomb.io/blog/production-is-where-the-rigor-goes). Don’t just check out production logs when there’s an error. Charity argues that production is the source of truth for your system and deserves regular observation.

[blog] Introducing the new full-stack vibe coding experience in Google AI Studio (https://blog.google/innovation-and-ai/technology/developers-tools/full-stack-vibe-coding-google-ai-studio/). This is exciting. This is a killer tool for anyone who wants to take an idea and build a legit web app to implement it.

[article] We mistook event handling for architecture (https://www.infoworld.com/article/4145032/we-mistook-event-handling-for-architecture.html). Did we all get too focused on event paths and handling in our architectures? This article shows how frameworks and thinking has evolved.

[blog] Do Large Language Models follow Benford’s Law? (https://medium.com/google-cloud/do-large-language-models-follow-benfords-law-c47c9f0f9070) Now I know what Benford’s law is. Apparently most distributions skew heavily toward numbers starting with 1 or 2. Do LLMs respect that?

[article] What the Best AI Users Do Differently—and How to Level Up All of Your Employees (https://hbr.org/2026/03/what-the-best-ai-users-do-differently-and-how-to-level-up-all-of-your-employees). Really good. What do sophisticated AI users do? I like the list, and was surprised that manager+ people are doing the best here.

[blog] Developer’s Guide to AI Agent Protocols (https://developers.googleblog.com/developers-guide-to-ai-agent-protocols/). This throws a couple extra that you might not always hear about. With examples!

[blog] Using skills to accelerate OSS maintenance (https://developers.openai.com/blog/skills-agents-sdk). Some maintainers are giving up because of the flood of AI-assisted PRs. I can understand that. But others are smartly updating the tools and workflows at their disposal.

[article] The unwritten laws of software engineering (https://newsletter.manager.dev/p/the-unwritten-laws-of-software-engineering). What’s some tribal knowledge that never gets a fancy label, but we all kinda know it? Good list here.

[blog] AI shopping gets simpler with Universal Commerce Protocol updates (https://blog.google/products-and-platforms/products/shopping/ucp-updates/). There’s a lot happening in this space and we’re continuing to improve this agentic protocol.

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=29037)