Author: Richard Seroter

We survived the SoCal tropical storm and are back to sunshine today. It’s a full reading list today, with a lot of pointed opinions!

[blog] Good Intentions Aren’t Enough. A major takeaway here is that we should often pause when your instincts kick in and not immediately jump to action.

[blog] The Standup Your Agents Can’t Attend. Agents can only work with the data it has access to. That doesn’t mean keep your meetings away from the agents. Change how you work.

[article] Google Gemini Agent Puts the Agent Ahead of the Model. We’ve made our bet. Google has a fairly unique stack that doesn’t stop at the model.

[blog] It’s time to stop installing skills. Smart advice. Don’t just install a skill, which in essence is someone else’s checkpoint. Edit them as your own work progresses and improves.

[article] As AI agents grow, vendors carve out decision-making as a separate model layer. It’s not just about the LLM anymore, but these AI stacks stand to get (unnecessarily?) complicated.

[blog] Bravery Recession. yes, real bravery where there’s the presence of risk. I like the advice about surrounding ourselves with people who also do hard things.

[article] Your AI agents can execute every tool call correctly and still break every enterprise rule. Governance, evaluations, and all sorts of boring things matter a ton. Invest here if you really expect AI to scale at your company.

[blog] Muse Wonder. Looks like the first frontier model from this crew. Meta spent the money to build up the AI talent, and it seems to be paying off.

[blog] The State of AI Report 2026. Big report. It looks at the work of the major labs, but also where we’re heading with robotics and more.

[blog] Does better work always mean better workers? Somewhat. Experienced people got better when using AI, and retained that when AI went away. Junior staff? Not so much.

[blog] Why In-Person Tech Conferences Still Matter. Indeed. Even if we’re talking local events, prioritize face-time with other people in your field.

[blog] 10 Years of the SRE book: Announcing the second edition of “Site Reliability Engineering.” The first edition was a hit across our industry as it codified some key practices. A lot has changed, so it’s time for v2.

[blog] Do Agent Teams Pay Off? A Case Study on Vibe Code Bench. Not always, and it seems valuable to assess whether you’re over-processing the problem at hand.

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

Happy Friday. Today’s list doesn’t have any “use this product” focus, but is more about techniques and topics to thinking about.

[article] Building scalable, agent-friendly APIs for AI applications. APIs are just APIs, right? Regardless of client? Sort of, but agent calling patterns should force us to revisit a few assumptions.

[blog] If your team is happy, are you doing a good job? Wow, there’s a lot here that needs to be said. Our job as managers is to get business outcomes, and ideally making it awesome for our teams too.

[blog] if your team is too busy doing their ‘normal job’ to experiment with AI, you’re preparing them to be replaced. Needs to be said. If you plan on being employable in tech, you should be proficient with AI tools.

[blog] Deno is joining Cloudflare. Congrats to the team. This looks like the end of Deno though, as this JavaScript runtime will only be supported for the next twelve months now. Then the hope is that it keeps going via pure open source.

[article] The 6 Essential Skills Your Workforce Needs to Keep Pace with AI. This part seems pretty clear. Those who do strategic and systems thinking, mixed with applied expertise and judging AI output, will be best set up for the future.

[article] What does it take to keep an LLM judge trustworthy in production? Can the LLM just be the judge instead of requiring human evaluation? That judge needs curated training data and more. Which means humans still play a role.

[blog] The Outer Loop, Insights First: An Ambient Quality Agent That Diagnoses Your Production Agent. Some are experiencing it, but pretty soon many will find out that “all green” dashboards aren’t telling you that your AI agent is falling apart. This quality agent helps find those signals that the agent is off track.

[article] 7 Things that I Encourage as a Manager. There are all sorts of ways to manage. If you’re new at it, consider these situations to encourage.

[blog] How much does it cost to use open source software? This feels like unique research. How long does it take an engineer to update an open source package at Google? Sophia’s on my team and does great exploration of OSS.

[blog] Why I tried to kill token billing (and why we kept it). Is output-based billing much better than pricing products with passthrough token costs?

[article] Don’t measure AI Code Percentage on its own. How should we think about this metric, or not? This seemed like a good take.

[article] Agentic Primitives 101. It’s good to review the foundation, as it keeps us from freaking out over the perceived complexity of the higher order thing.

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

We had a big Gemini event today, and plenty of other interesting things are going on around the industry.

[blog] Welcome to Gemini at Work 2026: Introducing the Gemini agent. Big play for us. A central, universal agent that pulls together unified context, has cloud for async work, and real security/cost controls? Yes please.

[article] What Actually Sets High Achievers Apart? Fascinating thesis which seems obvious once you process it. Trying to change your situation (physical environment, team, mentors, boss) has more impact on performance than just altering your mindset.

[blog] How to build an AI-native software factory. What’s left to build? For many, it’s the system that builds the software. Lots of details here, with a focus on what’ Uber is doing to build a software factory.

[article] Five keys to controlling AI token costs. Not new, but maybe new to you. More of these ideas will keep coming.

[blog] Supercharge your development with the Google Developer Knowledge API ecosystem. We’ve been working hard to give you trusted info, how you want it. Now you can pull the latest Google documentation (across two dozen domains) via REST API, MCP server, or the Google Cloud CLI.

[blog] Anti-Patterns in Software Blogging. Absolutely fantastic post. These are all things we need to stop doing in our writing if we care about landing a message.

[article] Redis by proxy: Percona targets the last major hurdle to Valkey adoption. Migrate from Redis without rewriting any of your app. That may trigger more people to make the leap to Valkey.

[blog] Part 2: Evals as a deployment gate — and how to know when they drift. have you started thinking about evals the same way you think about tests? Continuous applied and a gating function for releases?

[report] The State of CI/CD in 2026. Mildly related to the previous item. What are we doing with CI/CD right now? The JetBrains survey provides the answers.

[blog] Private AI Won’t Be the Center of Your AI Universe. Hybrid Will. Good points from Keith regarding where the various components of an AI system run.

[blog] Thundering herd of circuit breakers. Great title and fun log from Zalando engineers who had to troubleshoot why a circuit breaker was staying open too long.

[article] Ben Affleck is an AI nerd, and the internet is impressed. I’m definitely impressed. He could do my job tomorrow. Alas, I could not be a good Batman tomorrow.

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

I don’t have a ton of family living close to me, so I’m stoked to have dinner tonight with my visiting brother on his birthday. All the stuff below matters to me; my family matters to me much more.

[article] The state of the tech industry in 2026. Excellent look at where things stand today, at least with regard to software development. There’s a whole other set of topics (data, inference, operations) that deserves the same treatment!

[bog] Inference Is the Most Important Market in Software. Does inference matter more than the database category? If we go by revenue, yes.

[blog] Introducing Playground: Create and play custom games. Amazing. Genuinely. I’m excited to build some games with my kiddos.

[blog] Wake Up to Clean Branches: Automating Your Dev Routine with Antigravity 2.0 Scheduled Tasks. Neat demo. I’d imagine that I’ll only use these scheduled tasks when my machine is always on, or when I can run them cloud-side without worrying about it.

[article] Companies are building governed semantic layers. Most say their AI agents are getting context somewhere else. Direct queries to systems, along with documents represent most of the sources called out in this survey. Too early for wide adoption of trusted data layers? Assuming they even exist?

[blog] Shipping is the foundation. Learn how to ship. Everyone needs this mindset, and everyone in tech needs the ability.

[blog] Announcing MCP Toolbox Java SDK v1.0: Agentic data access for the enterprise. This acts as a client for your remote instance of the MCP Toolbox. Super useful when you’re bringing data into your agentic Java apps.

[article] The next hurdle for AI agents: getting websites to let them in. Personal agents are suddenly getting the stiff-arm from websites. Something’s gotta give. Sounds like some new proposed standards are floating around.

[blog] Building Git infrastructure for agent-scale development. Few stacks were built for the type of traffic (and behavior) that agents bring. Here’s how GitHub is evolving.

[blog] Migrating from MongoDB to Firestore Without Changing a Single Line of Code. My last two app builds have depended on Firestore. Great database.

[blog] Dreamforce 2026. The personas are flattening, and user interface isn’t the moat. Both are important takeaways from this post.

[blog] Introducing Google Cloud Modernize, transforming for (and with) AI. Modernization got easier with AI. There’s still probably a structured flow you want to follow as you do discovery, stack selection, and monitor the transformation.

[article] 12 things I miss since coding died. This resonated with me. At least most of the list. It’s ok to reflect and admit that we’re losing something with more automation. And also gaining other things.

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

I “built” a demo system in the background today while getting my other work done. It was fun to dip in every half hour and review the agent’s progress, ask questions to better understand what happened, and then approve the next steps. I could get used to this.

[article] Do you really need another framework? Maybe? This is one for your context and whether you’re giving an agent anything good.

[article] CAFE(S): Your Agent Is Only As Good As Its Context. Learn more about the above framework by reading this paper from us and others.

[blog] EmbeddingGemma 2: an open, lightweight multimodal embedding model. Very unique, and potentially very useful. Work entirely locally on device and across modalities (text, image, video, and audio).

[blog] AI For The Public Interest: What A Quarter Century Of Global Television News Can Teach Us About Our World. What if you ask AI to watch decades of television news across 75 countries? That’s a fascinating pool of data for insights.

[blog] The 4 levels of agentic software development. For most companies, their differentiator won’t be model capabilities; it’ll be how they change the way software is built. These four levels factor that in.

[article] Mistral debuts Large 4 ‘Le Chonk’, a 1-trillion parameter text output model with high benchmarks planned for open weights release. Top tier naming. Le Chonk. The numbers look impressive here, which is only good for buyers.

[article] There’s No Such Thing as an AI-Ready Culture. These are five dimensions to look at, but no exact “right” culture, but there are muscles to build.

[blog] How To Stop Getting Taken Advantage Of: 6 Secrets From Game Theory. Most of us could use this advice. Acting too nice or avoiding conflict? That probably means you’re losing in every situation.

[article] Knowing which vulnerability to fix first. Because you probably can’t get them all, you need to think carefully about which vulnerabilities to focus on.

[blog] The results of the 2026 Developer Survey are here! Still a big deal, even with StackOverflow down from its former glory. Many insights into developer adoption and trends.

[blog] Data is the application. Interesting POV. With agentic coding you can make or remake just about everything in no time. But data? The lack of it, or management of it, requires more care.

[blog] Cloud Run’s invisible 60% scaling dials are now yours to control. With good software, the default configuration values are set where they are for a reason. But you may want to override them based on what you know about your system.

[blog] Beyond synthetic testing: Capturing and replaying real database workloads at Airbnb. I love engineering blog posts like this. Here’s how Airbnb updated their query capture system.

[blog] Two-Way Doors: Don’t Code Yourself into a Corner. Don’t over-engineer everything for ultimate flexibility, but also don’t paint yourself into a corner.

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

I’ve got a lot of AI agent content today. Especially around memory and storage. That feels like an area that’s very fluid right now.

[blog] Are AI agents the new platform engineering customers? Sure. They need to discover services, follow golden paths, follow policies, and more.

[blog] The Sandbox is Inside the Score. This is a great area to invest some of your time into. Learn about evals, platforms that support them, and how to set up a continuous eval loop.

[article] The Future of Software May Be Conversational Rather Than Autonomous. Good counterpoint to the feeling of inevitability that “the natural end state of AI is autonomy.” Maybe not.

[article] AI is less dangerous than humans. Yes, it’s somewhat amusing to observe our narcissism in the AI era. “How dare these AI agents do a fraction of the damage humans are capable of!” Safety matters all around. So does innovation.

[blog] We’re going to need default hard budget caps on pretty much everything. Just like I know how much I can spend when I go shopping, my agents need the same limits on their spend.

[article] Google’s WikiSkill gives AI agents a memory of what went wrong — without putting it in the prompt. Better than “just” agent memory? Or even as a replacement? Maybe. Watch this area, as a lot of exploration is happening.

[blog] Agents Don’t Need Memory. They Need Documentation. Related to the previous item. Very good argument for “documentation over recall.”

[blog] How to implement long-term AI agent memory in AlloyDB and Memorystore for Valkey. Ok, last item on agent memory today. But hee’s how you might do an explicit memory architecture based on short term session data and long-term persistent memory.

[blog] More on Antigravity as a PM’s best friend. Yes, your product managers should be using AI too. But how? In what way? Mark shares his rea-life use cases.

[blog] Meet the A2A CLI: discover, message, and manage agents from your terminal. Very cool. This looks like a genuinely helpful CLI that you might plug into your coding harness or agent workflow.

[article] The Mindsets Leaders Need as AI Accelerates the Pace of Business. This is the part of AI transformation you can’t buy. That makes it uncomfortable. But you won’t win without this mindset change, regardless of how much you spend.

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

Bigger list today as I try to clear out the queue. Too many great pieces lately! I’m still starting a dozen open tabs I need to read over the weekend. Could be worse.

[blog] React Native solved a problem nobody had. Use Flutter. Fundamental points being made here. If you want native, don’t use a proxy for native. But if you want a rendering engine for owned experience, that’s a case for Flutter.

[article] Meta’s next big AI bet is enterprise; its biggest hurdle may be trust. To be fair, it’s everyone’s hurdle. Everyone selling AI is also selling their trustworthiness with your data and actions. Hard to build, easy to lose.

[blog] Spanner Omni, now GA: A distributed, multi-model database that you can deploy anywhere. This is possibly the highest performing database ever created. And now you can run it wherever you want, including your laptop.

[blog] Can You SEO Your Way Into an AI Agent’s Recommendation? I’d bet that one or two things in here surprise you. They surprised me when we got the data.

[article] How do AI coding assistants change the shape of engineering work over time? This reiterates findings I’ve seen elsewhere, even inside Google. The work changes in a few ways, and you need to actively account for it.

[blog] Introducing the Server Side Cloud Swift SDK. Swift isn’t just for UI work on Apple client devices? I’m not sure I knew that. We just shipped an SDK for those who want Swift’s concurrency benefits on the server.

[blog] Why redesign doesn’t happen (enough). Sounds like a realistic story to me. What can remove the fear of making changes, breaking other PRs, and getting stuck in merge hell?

[blog] Devs are coding faster. Coding reviews are eating the gains. Some very sensible advice, with more specifics than I expected.

[blog] GKE CPU startup boost: Accelerate app starts without over-provisioning. This is the way. It’s similar to something we offer for serverless Cloud Run as well. Get a little extra CPU juice during startup.

[article] Survey Surfaces Sharp Increase in Amount of Code Written by AI. Some pleasant surprises in this data. Devs are spending less time coding, but more time learning. I like that 86% of devs find their new work more fulfilling.

[blog] Announcing Spanner queues: Transactional messaging for agentic workloads and beyond. Messaging geeks (me included) have feelings about using databases as queues. But there are real use cases, and this is sweet functionality.

[blog] How our vibe coded website looks like a designer made it. Will all websites look alike soon if we’re all using AI tools? Not necessarily. Especially if you do it right.

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

I’m at the airport waiting to fly home after a day trip up the Bay Area. After a few hours with a fantastic audience at the local DevFest, I spent the late afternoon with customer execs who wanted to talk about software engineering with AI.

[blog] The Code Nobody Reads. Big piece, worth reading. Code review is changing, but the key will be knowing what’s worth reading and reviewing.

[blog] Create an Agent that Remembers with Agent Platform Memory Bank. It’s going to be important to know how to store and reuse memories. This is a good service to consider.

[article] Maintaining quality while agents write the code. Somewhat related to the first item here. We’re going to need to zoom in on the decisions that require thoughtful instructions and reviews.

[blog] Your Enterprise Agent Talks Too Much. Give It a UI with A2UI on Cloud Run. I liked the framing here. Give more focused answers through a generative UI.

[article] OpenClaw launches free enterprise control plane for persistent AI agents, backed by OpenAI, Red Hat and Nvidia. Give any product some time, and you’ll see an “enterprise” flavor. This makes sense.

[blog] Coding is NOT solved. Maybe a counter-point to other items listed here. We’re responsible for what we produce, whether we understand it or not. I don’t agree with all (most?) of this, but I’m glad to read the perspective.

[blog] Empower your agents with the Google Cloud CLI remote MCP server. CLI-over-MCP is an important pattern, especially when dealing with AI clients that won’t be allowed to call local scripts or CLIs to do stuff. I used this in my blog post from yesterday.

[blog] Cut your AI spend with AI Gateway’s Auto Router. Cloudflare is shipping lots of cool new things. Expect every major platform to offer capabilities like this one very soon.

[article] Observability for AI-native systems: New SLIs beyond latency and error rate. I’m not an ops person, but I’d imagine that serious people revisit what metrics they’re looking at, and don’t get stuck on the same set forever. Now’s a good time for one of those resets.

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

Last night, I went to the San Diego Padres playoff game against the Chicago Cubs. It was the rowdiest, loudest, most fun baseball game I’ve attended in my life. The downside? I’m very hoarse and had two major speaking gigs today. So yeah, I plan well.

[blog] Gemini 4 Argon: our next era of frontier intelligence. Are you not entertained? We shared information about this model. Numbers look … great.

[article] The best AI leaders are ‘a little bit off the wall,’ says Google Cloud executive. I did say that. Here’s a summary of some of the points I made in Boston a couple weeks back.

[blog] Build an agentic software factory, starting with one bug. As you build up a set of AI agents to help you with software, do it incrementally. Useful lesson here.

[blog] Graph Workflows in ADK: Everything You Need to Know. I liked this explanation of working our way up to more sophisticated agent architectures.

[blog] State of agent skills. Vercel sits on a lot of data here thanks to running skills.sh. Read this for a look at what skills people are installing, for which industries, and how often.

[blog] State of Markets II. We’re getting a bunch of “state of XX” things lately. The a16z folks call out a bunch of data about companies using AI, and more.

[blog] Vulnerability Discovery and Exploitation Trends in the AI Era. Sobering data about the rise in vulnerabilities, and corresponding increase in exploitation. At least there are suggestions for what to do next!

[blog] Voice Agents Can Just Do Things. I buy this more than I did a year ago. But I also don’t want this to be the ONLY interface. Sometimes it’s better to type things out, or I’m in a space where I don’t want to be barking commands to a robot.

[blog] Data Agent Kit is now GA: Bring Google Data Cloud to any coding agent. Do some fairly sophisticated analytics and data science work in whatever AI coding tool you prefer.

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