Category: Daily Reading List

It’s unusually hot and humid in San Diego, but that didn’t deter us from being outside this weekend. But, during some air-conditioned indoor time, I wrote up a blog post. You can count on it being outdated in like three weeks as the next new thing comes along.

[article] Our Favorite Management Tips on Learning from Failure. Solid tips. If you’re experiencing any failure, you might not be pushing hard enough.

[blog] Beyond Vibe-Coding. Your prototype might actually turn into something. Here are some lessons from one such case.

[blog] Top AI Trends Every Developer Should Know in 2026. None of these are earth-shattering (if you’ve been paying close attention to the industry), but I liked this roundup and it’s a good look at what matters right now.

[blog] The Code-Generation Percentage Your Org Shouldn’t Be Measuring. The “percent of code that’s AI-generated” is a lousy metric. It doesn’t tell you anything particularly meaningful. Casey gives us four alternative metrics.

[article] Enterprises bet on agents to build in-house software, boost productivity. It’s interesting that some big companies are moving faster than the small ones. It’s also not surprising that employees have the confidence to build more of the software themselves.

[article] How To Be Strategic: 5 Secrets From History’s Greatest General. Absolutely fantastic post. Does your manager say “think more strategically” and you have no idea what that means? Read this to start training yourself.

[blog] Understanding the Linux Kernel: Network Subsystem. I joke in customer meetings that this is exactly the sort of knowledge I’m now happy to forget. Higher abstractions have let me ignore it. But, it’s pretty cool to dip back down again and re-engage with it.

[blog] You have to beat the models at something. Right now, you’re better at LLMs in your familiarity of the tech details in the system in which you work, and at clear communication regarding that system.

[article] Effective Patterns for Advanced MCP Usage. This is promoting the idea of composing solutions out of multiple MCPs, using remote versus local, and more.

[blog] Who Taught the Models to Do That? Models are designed, not born. Good reminder. Models are designed for behaviors like persistence, note taking, and coordination.

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

Happy Friday. I’m at inbox zero, and hoping for a fun weekend with the family. And might write a blog post if the stars align.

[blog] Teamwork: When AI Becomes a Research Partner. This is outstanding. I liked the deep dive into the patterns this tool applies to agent teams. And the results are impressive.

[blog] Don’t Waste Your Career Getting Comfortable. Tons of good advice in here, much of which I follow diligently myself. Get comfortable being uncomfortable.

[blog] Dynamic capacity management for AI infrastructure. Now isn’t the time to commit to a ton of fixed infrastructure. Who knows what you’ll need in six months, let alone two years. Here’s a good post on embracing a more fluid foundation.

[article] AI Transformation Requires Redesigning Work, Not Cutting Roles. There’s good advice in here. Especially the examples of where companies go down the wrong path.

[blog] Simplify your resilience testing strategy with Fault Injection Testing. How you feeling about your disaster recovery plans? Tested them in a while? What about when you’ve got many workloads in a public cloud? Here’s a new way to simulate meaningful failures to see how your automated resilience handles it.

[blog] Friday Forward – Expert Silence. We’re all wrong—yes, even “experts”—all the time. It’s completely normal. But be smart enough to acknowledge new facts when more information comes in.

[blog] Designing Websites for People and AI Agents with WebMCP. I’d encourage you to be aware of WebMCP, even if you don’t want to go deep on it.

[blog] Unlock Antigravity 2.0: Logins, Plans, Cost, and Quota. Getting started with new tools can be intimidating, especially when you have a handful of initial choices to make. Alexis breaks this down in a very understandable way.

[blog] Introducing Agent Native Design: An Open-Source Figma Alternative. Build interactive prototypes that you can export anywhere.

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

One theme that emerged from today’s reading list? “Are you ready for AI.” Is your data ready? Your APIs? Your backlog? User experience? Your people? If you say “yes” to all of those, you’re a unicorn and I’m very impressed.

[blog] Intelligent transcription with Gemini 3.5 Transcribe. We just gave a big boost to your speech-to-text ambitions. I love how it handles rambling talk, background noise, and even custom vocabularies. Related, on voice interactions.

[article] One-third of employees overstate AI skills: report. Generational differences here, but we’re all trying to figure out what to use, and know.

[blog] Piloting the world’s first double-blind AI evaluations. At this point, I assume that models are trained to create great “pelican on a bicycle” images given how much that little test is talked about online. You need a way to eval where models haven’t already seen the test questions. Here it is.

[blog] 10 Tips for Preparing APIs for Agentic Access. Important topic! I like the areas called out in this post.

[blog] The Backlog Was a Coping Mechanism. Good post. I was taught “now, next, or never” for incoming requests and to avoid a bloated backlog that we’d never get to. Some of those considerations change further, as Allen identifies here.

[blog] Generic Methods. Go developers have very strong emotions about this one. Many love, a few hate. It’s ok. I’m happy that devs push us to keep Go straightforward to write and read.

[article] Making Your Data Ready for Agentic AI. Above we looked at making APIs ready. You need your data to be ready for AI as well.

[blog] Deploy personal AI agents with Cloud Run instances. This fills a specific need. You’ve got an always-on component, but want a fully managed runtime. These new instances are ideal for OpenClaw, Hermes, or whatever continuous and stateful workload you got.

[article] Harness Unfurls Source Code Repository Alternative to GitHub. Not the first, not the last. Let’s see if this new crop of source services have staying power.

[blog] Expert Intelligence: a new way for you to engage with trusted content. Load books into Gemini Notebook (aka NotebookLM) for more personalized learning. Cool.

[blog] AI UX Patterns to Show Meaningful User Benefit. How are you adding AI features to your existing app surfaces? Here are some patterns to consider.

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

Another good batch of items today that might impact how you train your people, share knowledge across teams, and pay for AI services.

[blog] What is harness engineering and why should I care? It’s not too late to ask, and even those who “know” can always learn more.

[blog] What’s the Difference between Generative Engine Optimization (GEO) & Agent Experience (AX)? “Regular” SEO still matters, as web search tools alongside LLMs pull top search results. But there are plenty of new considerations for what gets included in the LLM itself, and the overall agent experience.

[blog] Is the future of learning ‘vibe’ training? The focus of learning switches from “how” to “why.”This has impact on the trainers as much as the students!

[blog] Five monetization trends from global pricing leaders. Is your favorite tool seemingly switching up its pricing model more often? You’re not imagining things. Here’s what happening in the world of software pricing.

[blog] FinOps for the AI era: New flexible billing and cost controls for agents. Speaking of monetization, we’re going to keep working on ways to make products easier to pay for, while reflecting that how we consume these products is changing.

[article] You need to find product-market fit again (sorry). You’re probably never done finding or confirming fit. This post looks at how to proactively disrupt yourself to keep learning.

[blog] Gemini for Go Developers: Building Agents in Go. Daniela did the test I wanted to run, and did it better. Excellent assessment here of different ways to build agents.

[blog] Intelligence is the Primitive. Applications are the Diffusion Layer. Super interesting slides here, some of which challenged my own thinking on the topics. Particularly the moats (or lack thereof).

[blog] How Flutter stays ahead of iOS releases. If you build a product on top of a platform, you have to figure out how to be ready for each major platform release.

[blog] What language are agent skills written in? What an interesting question, and it produces a fascinating answer. Good read.

[article] Salesforce just put its entire CRM inside Claude — and says you’ll never need its app again. Cool move. Likely a harbinger of the future. Build more endpoints, and fewer frontends.

[blog] Using OKF with Knowledge Catalog to serve context for agents. In a meeting today, someone asked me how to distribute shared context. I had no answer. Then read this post and shared it.

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

I’m in Sunnyvale at Google Cloud HQ today and tomorrow. On the flight up, I finally got my generative UI service working properly in Gemini Enterprise. There are few things more satisfying that having an idea and then seeing it come to life with software.

[article] Google brings Antigravity under Gemini Enterprise to provide granular spend controls. This is the next frontier. How do we make AI work better within teams, not just for individuals?

[article] Can “Predictable Delivery” be measured? Interesting question. Two teams could have wildly different output per sprint, but have the same throughput over time.

[blog] Now introducing Gemini Enterprise for Financial Services. Smart offering, and you’ll see more things like this. Industry-specific AI is still in the early stages. See our legal offering as well.

[blog] The Mundanity of Excellence. Love it. Mundane tasks done over and over again don’t have to “boring” if you attach meaning and purpose.

[blog] Cloud CISO Perspectives: Sticking to security fundamentals in the AI era. CISO’s are more valuable than ever, if focused in the right places. This gives some perspective, along with many links for deeper learning.

[blog] Human judgment doesn’t leave the software factory. It relocates. Long post, but very worthwhile read from Addy. If you keep hearing this “software factory” phrase but aren’t sure what it means or when you’d use it, read on.

[blog] Architects, testers, and coders: Building multi-agent development teams. Andrew uses an agent team to port a popular Python library to a statically-typed Dart package. He experienced friction, iterated, and ended up learning some things. Good experiment!

[article] The AI-Native SDLC playbook. Fascinating writeup from Anthropic where they explore the SLDC stages with AI-lens. Same “work” but done very differently.

[blog] Deploy your App Engine apps to Cloud Run in a single command. When people find a stack they like, it’s hard to get them to switch! 15+ years after launching it, we still have a hearty customer base. This post shows the one-line command to switch over to the more modern Cloud Run.

[article] Not every problem needs an AI agent. Blasphemy, I know. Valid points here, but I also wonder if the box the author puts AI into will quickly dissolve.

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

In between meetings, I had a chance to refresh some demos ahead of a customer presentation this week. And, to iterate for a while (too long) getting a generative UI agent to give me a custom interface in Gemini Enterprise. I’m glad my coding harness doesn’t get frustrated as quickly as I do.

[article] 20 Lessons From 20+ Years in Tech. Really good. We need to be reminded of these lessons, and be more intentional about how we go about our professional lives.

[blog] Event Driven Architecture and Coupling: You’re Not as Decoupled as You Think. Decoupling your internal API as a series of event-driven messages isn’t buying you much. Good post here on modeling around business concepts and behaviors.

[blog] The Case for Software Craftsmanship in the Era of Vibes. Sure does. Regardless of what you may see, “software” isn’t solved just because of AI. There’s a lot that goes into system design, product thinking, and building high quality software that matters.

[article] Most coding agent benchmarks skip large-scale refactoring. Not this one. This seems like a solid benchmark for complex tasks. LLMs aren’t doing that great at it. Yet.

[blog] Summary : Where does Antigravity look for configurations? If you use a handful of AI tools, you’re probably copying files around between locations because the industry hasn’t standardized on where we stash configs.

[article] How should engineering leaders measure the ROI of AI? All-important question. It’s not about how much AI you’re using. Who cares? It’s how much value you’re getting.

[blog] Meet the Antigravity Extension: Gemini Code Assist on Steroids, in Whatever IDE You Love. It’s not true for everyone, but for many, the IDE is now mostly a read-only code viewer. I’m glad we’re putting our coding agent in your IDE of choice.

[blog] Three Clouds, Three Native Agents. A telling effort. William looks at coordinating agents across the three major hyperscalers.

[blog] How to Evaluate Live & Voice Agents in ADK. I’m sure there are solutions out there, but I haven’t seen them. This is a great way to test live/voice agents and prove they follow the desired path.

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

I ended up with some open time today to build, which felt good. Maybe some more this weekend, but the weather might be too nice to stay inside. Good thing I now have Antigravity Remote Control 🙂

[blog] AI Conversation Trajectories: An Indispensable Primitive & A Terrible Name. We’ve settled on “trajectory” as the name for a completed AI session. Ali hates the name, but recognizes how important this resource is.

[blog] Antigravity Anywhere with Remote Control. So awesome. Now I can access my machines running Antigravity from anywhere. It’s got full awareness of my projects and local context, and I can do most anything from the web interface.

[article] This post will save you tokens. I would behave differently if I was paying for all my tokens right now. Including following some of this advice.

[blog] Building Agents in Go: Where Genkit Shines vs ADK 2.0. Both of these frameworks are great, and heck, both by Google. But there’s a place for each.

[blog] Why I Tell My AI Coding Agent: “Prefer Dart Over Python”. Hear this person out. The argument is pretty good!

[blog] Good writing is obvious, not original. Just write clearly; that’ll stand out more than trying to for originality at every moment. And share things that are obvious to you, but maybe not others.

[blog] Inside the Gemmaverse: Celebrating one billion Gemma downloads. I like that this post celebrates some rad things people built with Gemma so far.

[article] AI productivity gains aren’t translating to IT workload relief. The four-day workweek isn’t on the horizon. As you can get more done, more work shows up.

[blog] Stripe to Acquire OpenRouter: Why Everyone Is Obsessed With Model Routing. A bit of a look at this recent acquisition, but also a nugget about why good routers have data that helps them proactively redirect your requests.

[blog] Bringing Primary Constructors to Dart. Yes, new language features matter, even in the AI-writes-all-the-code era. Easier readability is still important.

[blog] Inside Android Skills – Built for deprecation. I’ve got strong opinions loosely held regarding skills. Useful, yes. But a new type of durable documentation? I don’t think so. I’m more aligned with this post’s POV.

[article] Salesforce wants to move AI coding into a shared workspace with Slack Code. Smart. It’s a place (Slack) where a lot of devs already spend time. Don’t make them switch surfaces. More here, from Slack.

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

I’m adding things to my “you should try this technology” list much faster than I’m getting through it. At some point I’m going to declare bankruptcy and start over. Tomorrow’s looking like a clean “no meeting day” so I stand a chance to get through two of my top ones. Stay tuned.

[blog] Expanding Google Antigravity for enterprise customers. Now Gemini Enterprise users get the Antigravity harness across their favorite IDEs, pooled usage among teams, and backend enterprise controls. More here.

[blog] Practical Loop Engineering. Educational post on the type of agent loops, and how Addy applies them in his own work.

[blog] Add telemetry and observability to your AI agents. Does it really make a big difference to give your agent a memory? Jason built a reference system to test it out and see how behaviors diverge over time.

[article] Your coding agent got the onboarding your developers never did. I chuckled at the headline, because it hit home for me. Are we giving better budget, sponsorship, and patience to agents than we did to humans? Probably.

[blog] How Google Cloud MCPs Give Claude Code Inside Access. Investments in skills and MCPs shouldn’t be tool specific. The whole point is to make sure anyone can use them. Here’s one example.

[article] Only daily AI users feel positively about job security. I guess that doesn’t feel surprising. Those embracing and using the latest thing are likely more future-proofed.

[blog] 20× the CI traffic without getting slower: How we rebuilt Git serving at Datadog. You probably don’t have a git setup as complicated as this. But there are good lessons on unnecessary cloning, recognizing that CPU is the bottleneck, and being smart on your fetching strategy.

[article] Is Your Organizational Culture Too Nice? You know what this looks like. Bland feedback. Everyone gets great performance reviews. Everyone gets a voice. Stop that. Care deeply about others, while aiming for candid, results-focused kindness instead.

[blog] How AlloyDB ScaNN scales vector search to 10 billion vectors. Tremendous performance for a relational database. Here’s how we did it.

[article] When Your Buyer Is an AI Agent. Time to challenge your existing assumptions on pricing and managing buyer relationships.

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

I had jury duty today. Our pool of potential jurors wasn’t needed, so another year without serving. That might be best for society.

[article] Enterprises with AI context layers report agent failures at more than twice the rate of those without one. “Response correctness” is super important to enterprise buyers. And probably all of us. Building these context layers takes time.

[blog] The Unreasonable Effectiveness of Docs in Product Development. Write the docs for the product you want to have, and then start building? There’s something there.

[blog] Harnesses are Situated Agents. The harness is where it’s at, as there’s a lot to manage and those layers are critical.

[blog] Gemini for Go Developers – Part 2: Coding with Gemini. This post will get you all the information you need to use AI to build Go apps.

[blog] Cursor Origin review: An engineer’s perspective. Ready to bounce from GitHub? It’s likely too early to make a big move to Origin, but it looks promising. More about Origin here.

[article] What the Microservices Era Can Teach Us About AI. You might share some lessons, but don’t accidentally treat these paradigms the same.

[blog] Go 1.27 is released. Highly anticipated update! We introduced some great language changes, and improved the already-awesome standard library.

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

Long day. Not done yet as I host my monthly all-hands calls in both AM and PM times to catch our global team. Fortunately these calls are fun, and it’ll distract me from a day of navigating corporate mazes.

[blog] AI usage patterns in software teams. Quite interesting data about the breadth of roles (and levels) using AI regularly. And what’s NOT changed.

[blog] AI Code Review Best Practices. Every team will do their own thing, but here are some viable techniques that work for this team.

[article] Nobody’s Actually Prioritising ‘Value’. Oooh, I like this take. “Value” is contextual to the recipient, and can only be measured after the value exchange occurs. We’re prioritizing work based on confidence in our hypotheses.

[blog] Build zero-trust AI agents with Google’s Agent Development Kit. If you’re using AI to generate AI agents, your tool might skip over this sort of guidance. Don’t make that mistake. Explicitly feed this in.

[article] A better approach to generative UI. Don’t just render out HTML/JS from your LLM. There’s all kinds of risk with that approach. Without saying so, this article makes the case for A2UI.

[article] A Home for Personal Context. Where does context live? Locally on a laptop? On the web? Or in your pocket? Probably all, in some way.

[blog] Google ADK 2 Graph Workflows: A Complete Guide with Code Examples. Romin goes deep here in a very readable post. Define deterministic steps, but still implement a variety of patterns.

[blog] When the Hard Part Stops Being Hard. AI changes how long things take to do. We’re coming to grips with what that means to publication volume, research value, and our intellectual ambition.

[blog] How I Planned an Italy Trip with an Agentic Workflow. As the AI interfaces get simpler, these types of use cases will explode.

[blog] Stop burning tokens on code review. It’s where you’re using the most tokens today in the SDLC. Use a cheaper (local?) model, create custom linters, or design this process with cost in mind.

[blog] Staying Ahead of Adversarial AI Through Agentic Source Code Review. It’s almost guaranteed that you’re piling up more code now that it’s easy to produce it. How are you scanning it at scale for vulnerabilities?

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