Author: Richard Seroter

… and now flying back home from Vancouver. Quick trip, but it was great to see my team (and local Google Developer Group leaders) hosting hundreds of techies who wanted to spend a day learning about AI and agents. The interest is real.

[blog] Introducing Nano Banana Pro. Goodness, what an amazing image model. Take a look, and see how to access it from a whole host of places.

[report] ThoughtWorks Technology Radar: Volume 33. I truly appreciate the work that goes into these, and I rely on them for introducing me to tech/concepts I was unfamiliar with. Great new edition!

[blog] Gemini CLI for Authors — Part 2: Defeat the “blank page” by generating a first draft with AI. As the writer of a few books and blog posts, I know the anxiety of staring at a blank page. I’ve found AI to be a great way to get started (even if I discard everything later).

[blog] Bringing the Office to the Terminal. Why break flow when you don’t have to? This new Gemini CLI extension for Google Workspace lets you read content, send messages, or look at your inbox without ever leaving your dev tool.

[article] Open-source developer burnout fuels supply chain risks. It can definitely be thankless work. I’m running our Open Source Program Office at Google now, and going to be spending much more time in this area in the months ahead.

[blog] Building with Gemini 3 in Jules. The product continues to be interesting to me, and fun to use. And now it’s more powerful.

[article] What’s in a Name? A Lot, Actually. Here’s How to Pick the Right One For Your Company. I’m not good at naming. At all. Apparently the same goes for many folks creating tech startups 🙂 But the advice here might help.

[blog] Google Named a Leader in the Gartner® Magic Quadrant™ for AI Application Development Platforms. Super strong performance from us here, and it’s based on some impressive in-house technologies.

[blog] From Gemini CLI to Antigravity: Why Agent Manager is the Upgrade I Didn’t Know I Needed. Great walkthrough and it demonstrates why this tool feels different. It’ll take time to adjust, but maybe less than we think.

[blog] Critical Thinking in the Age of AI. I see a lot of posts like this nowadays, and they good reminders to keep upleveling our thinking, and not assume that low level knowledge (alone) stays valuable over time.

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

I’m flying up to Vancouver (Canada) this evening to participate in a DevFest event. So many new things to talk about! I’m hoping for good airplane wifi so that I can do some deeper work with Google Antigravity. But I’m not getting my hopes up.

[blog] Gemini 3 Prompting: Best Practices for General Usage. Very good, specific tips from Philipp here. I’d imagine that a handful of these could apply to other models, but try them on Gemini first.

[blog] Three Years from GPT-3 to Gemini 3. Such a great post. The reflection of how far we’ve come, and the continuous mindset shift needed, is very valuable.

[blog] App Engine scaling, simplified: Map your scaling controls to Cloud Run. “If it ain’t broke, don’t fix it” is sometimes a valid approach. But sometimes even working things should be revisited. Here’s a good post on getting your Google App Engine workloads over to Cloud Run.

[article] How to automate the testing of AI agents. There’s some good advice here on rethinking QA and how to ensure you actually have “working” agents.

[blog] Google’s 2025 Accelerator Impact Report is here. Some staggering impact here, and we’re not slowing down.

[article] Our Favorite Management Tips on Leading When You’re Overwhelmed. These are all good pieces of advice. We’ll see if I’m too stubborn to adopt some of them.

[blog] Cross Language A2A Agent Development and Testing. This still feels like “the hard way” at the moment, but it’ll get rapidly easier. The fact that you *can* do cross-platform agent coordination is still a big step forward.

[article] Shadow work in engineering teams. There’s probably some amount of work that’s always “invisible” but when it’s a majority of the work, that’s a problem. All of a sudden, everyone is over-allocated because a manager doesn’t see that capacity as already accounted for!

[blog] The Dawn of the 10x Team. This is definitely better than a 10x individual, which mostly doesn’t exist. Can the focus instead be on how to empower teams to do incredible work?

[blog] Deploy apps to Google Cloud Run. Shopify adding this to their documentation, which is cool to see.

[blog] Don’t Fear Being ODD—Embrace Observability Driven Development for Faster, Safer Innovation. I’m trying to recall if I’ve ever heard of observability-driven development. i don’t think so. The point is valid, but not sure any developer is going to think about this a TON up front.

[blog] My Foreword to “Frictionless.” This looks like a terrific book by people who know what they’re talking about.

[blog] YugabyteDB Joins Google’s MCP Toolbox for AI Agent Development. This MCP server now connects you to a full spectrum of databases and makes it easy to bring data to your agents.

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

Amazing launch day for Gemini 3 and more. Check out more about that, and other interesting happenings.

[blog] A new era of intelligence with Gemini 3. Super overview of the monster set of announcements today.

[blog] Start building with Gemini 3. Text and media are important parts of any modern LLM, but coding is what most folks were watching from us. Logan explains how we’ve stepped up our game for builders.

[blog] Introducing Google Antigravity, a New Era in AI-Assisted Software Development. Speaking of that, this is the most important release of the day (to me). It’s an entirely new way to build modern software.

[blog] Bringing Gemini 3 to Enterprise. We’re good at ensuring that new models are available simultaneously in the places that matter most.

[blog] Gemini 3 brings upgraded smarts and new capabilities to the Gemini app. These are some legit upgrades to the experience, and once again open the door to new use cases.

[blog] 5 things to try with Gemini 3 Pro in Gemini CLI. Fantastic list of new things to try. That fifth use cases is eye opening.

[blog] What Technical Debt Means To IT Professionals. How do you define tech debt? Most realize that it goes far beyond old code. This post digs deeper and offers some ways to escape.

[blog] Only three kinds of AI products actually work. Early days. We’ll go from “doesn’t work” to “works” fairly quickly.

[blog] Rich and dynamic user interfaces with Flutter and generative UI. Use a library that’s connected to what we’re doing with the Gemini app interface.

[blog] How to build your own resume reviewer with Google AI Studio in minutes. There are few things that can one-shot an application better than Google AI Studio.

[blog] Chamber 🏰 of Tech Secrets #55: Issue-Driven Development. When you’re hands-on with these tools (versus simply observing) you tend to develop pragmatic practices. I like how Brian is thinking about directing his agentic workflows.

[blog] On Cursor, Erich Gamma, VS Code forks and the surprising role of the Eclipse Foundation. Open extension ecosystems (outside of VS Code) will play a big part in the upcoming years. While lots of tools depend on VS Code forks, you don’t want to be dependent on Microsoft’s control of an ecosystem.

[blog] Local code meets cloud compute: Using Google Colab in VS Code. This is low-key a big deal. Millions of people use Colab regularly, and this gives them an additional surface to work in.

[article] Go team to improve support for AI assistants. Go is already an excellent choice if you want to generate quality code with AI. Or build agents. We’re going to keep investing there.

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

I came into the day with thirteen meetings on the calendar, and planned on playing defense all day. Then a couple dropped off and I was facing free time. Went on offense by getting to Inbox Zero again, and building a few interesting things. Not bad!

[blog] why agents DO NOT write most of our code – a reality check. Why is AI not writing most of the code at this company? They still use AI, but for brainstorming, tab completion, and tasks like that.

[article] Do newer AI-native IDEs outperform other AI coding assistants? PR throughput alone won’t tell you what’s happening. But here’s a good investigation into these tools.

[article] Jevons or Bust. Is this a boom-or-bust cycle, or have lower prices and increased efficiencies actually driven a massive surge in AI demand? The a16z folks take a look.

[blog] I’m proven wrong on Playbooks and Google ADK. Many of us are rapidly assessing new frameworks and tools. That means we can miss things. Lak got new information, and is now bullish on ADK for agent building.

[blog] 2025: The Year Context Became King (And How Developers Are Wielding It). We’re not at a final state on how specs and context should look or behave. But we’re learning quickly!

[article] AI leads to a platform engineering revival at KubeCon NA 2025. AI at scale within a company is going to demand a platform approach. Good time for platform engineering skills.

[blog] Event Streaming is Topping Out. This is mostly focused on Kafka, but does show that event streaming MAY have peaked a couple of years ago.

[article] What’s 🔥 in Enterprise IT/VC #472. You’ll find the usual great insights from Ed here, but I liked the up-front advice on impactful presentations.

[blog] The Next Stage of AI Coding Evaluation Is Here. The gang behind the LMArena are introducing a new way to evaluate coding models.

[article] Your Top 2026 Priority? Prepare Your Data for AI. Good investment, whether you’re doing a lot of AI or not.

[blog] The road to useful quantum computing applications. I only loosely understand this space (and that’s even a generous description), but I’m paying attention to what’s going on. Maybe you should too?

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

Today’s list has some very cool things to click through and check out. Dig into a few of these!

[blog] Vertical Integration is the Only Thing That Matters. Developer tools don’t work in a silo. This post explains why integrations, or “glue code”, among these tools is so important, yet hard to achieve.

[blog] How to Train an LLM: Part 1. Long post, but educational if you want to follow someone’s journey to train an LLM and what was learned along the way.

[blog] Do you detect a pattern? BigQuery’s new MATCH_RECOGNIZE function can! Complex pattern matching, right inside your SQL queries? We keep adding functions to BigQuery that simplify your architectures.

[blog] What Developers Really Mean by “Bad Code.” Good question! This post calls out some criteria, and how to actively reduce the amount of bad code in your projects.

[blog] Introducing Code Wiki: Accelerating your code understanding. I really like this. The era of static (and often incomplete) documentation is over. Oh, a quality source of truth always matters. But how we consume it will never be the same. Check it out!

[blog] Ordering food using Zomato’s MCP server with Google Gemini CLI. i’m not emotionally prepared to order food via the CLI. Maybe next year. But MCP is opening up so many possibilities.

[article] Choosing the right format for your AI model: A comprehensive guide to AI inference formats. What are model formats, and why are there so many of them? It might feel too late to ask this question, but it’s not. Ivan taught me a few things here.

[blog] Nano Banana can be prompt engineered for extremely nuanced AI image generation. I often just one-shot silly stuff with our models, but this post does inspire me to invest more in refinement.

[blog] Spec-Driven Development: The Waterfall Strikes Back. It’s a legit concern, especially if people take the wrong approach with it. You can use specs to drive the next hour of work; don’t spend months writing specs!

[blog] Building Trustworthy Charity Agents with Google ADK and AP2. Great example of agentic commerce in action. Learn about the way it all works in this detailed post.

[blog] Waze keeps traffic flowing with 1M+ real-time reads per second on Memorystore. Some apps can tolerate a lag. Traffic and direction navigation data? Nope.

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

My goodness, today was bonkers. A dozen or so meetings, tons of exciting product updates to review offline, and a fire drill in the office. But the opposite is terrible (to me), so the non-stop action is perfectly fine.

[article] Mission, Vision, poTAYto, poTAHto. Really good. We can act like mercenaries who just get our job done, but I do like knowing there is a bigger purpose in mind. Jason provides a more down-to-earth way to arrive at that purpose and vision.

[blog] To get better at technical writing, lower your expectations. I definitely get the point here. You don’t have to be Shakespeare, or include every detail. Help the user quickly get the most relevant information.

[blog] Choosing Your Agent Framework. You can build your own, but there are many cases where a batteries-included agent framework is the right way to go. Allen gives an honest review of the options out there.

[blog] Building for an Open Future – our new partnership with Google Cloud. Hugging Face and Google Cloud are doing more together. Better model download performance, native use of TPUs, and more. Here’s our perspective.

[article] Overcoming the Organizational Barriers to AI Adoption. You can’t just hand your team AI tools and tell them to do better work. It doesn’t matter how good those tools are. Invest in training, frank conversations about roles, and prioritize areas that employees actually care about.

[article] Secrets of Performance Tuning Java on Kubernetes – The Article (Part 2). My friend Bruno looks at a few key configurations to ensure your Java containers scale and perform correctly on Kubernetes.

[blog] How to Build an Offline Agent with ADK, Ollama and SQLite. Great example of building an agent that can function even when the network is down.

[blog] Unleashing autonomous AI agents: Why Kubernetes needs a new standard for agent execution. From our open source team. Every Kubernetes distribution can take advantage of this now.

[blog] The Real AI Bottleneck Is Organizational Reinvention, Not Computing Power. Some very frank talk here from Forrester. I don’t think I disagree with any of it.

[blog] When Good Locks Go Bad: Diagnosing a System Meltdown Under Load. Good story from Flipkart’s engineering team. This is also why you really need to understand. your system architecture and code. Don’t outsource that to AI.

[site] Get inspired by what you can do with Claude. Here’s a very helpful set of use cases for whatever your favorite LLM is.

[blog] NotebookLM adds Deep Research and support for more source types. If your job involves any information collection and research—which tech job does not?—then you should be using NotebookLM.

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

Did you learn anything new today? Besides what I learned from reading the items below, I also got more insight into spec-driven development by trying my boss’ framework, Conductor. Pretty cool. I also got some fresh ideas about the AI SLDC after talking to some smart co-workers.

[article] The state of AI in 2025: Agents, innovation, and transformation. From McKinsey. This summary offers some insight into who is doing what.

[article] How to Make a Seemingly Impossible Leadership Decision. Some useful advice here. I’m learning that most decisions are reversible, and overthinking those causes unnecessary stress.

[blog] From Words to Worlds: Spatial Intelligence is AI’s Next Frontier. I found this post very exciting, and Dr Fei-Fei Li is leading some fascinating work into how AI will change how we interact with the world (real and virtual).

[paper] Context Engineering: Sessions & Memory. Here’s a completely free, ungated paper that packed with advice for those building stateful agents. 72 pages of goodness.

[article] AI is changing what it means to be a software engineer. This comes up a lot in my conversations with tech folks. What’s the job going to look like? How should we think about junior staff? What skills matter most?

[blog] How To Make Your Writing More Persuasive: 4 Secrets From Copywriting. Do these things if you want people to pay attention to what you write.

[blog] Running high-scale reinforcement learning (RL) for LLMs on GKE. Many (most?) won’t need to do at-scale reinforcement learning, but those that do will care about this stack a lot!

[blog] An Alternative Chat UI Layout. Do we need to rethink “chat” now that there’s more data stuffed into the back-and-forth conversation? Should “thinking” and other processing steps be separated out? I like the ideas here.

[article] Productivity Is Messing Around and Having Fun. Glad to hear it. Software development should be fun, but it takes work to set up a developer experience that makes it feel that way.

[blog] Progressive Delivery, the book, is here. Great topic, and glad to see this now available for everyone to learn more about this key idea.

[article] Agentic coding with Google Jules. Who knows what form all of these tools take in the year+ ahead, but there’s a distinct value to having AI that can do background work for you.

[article] How much does AI improve development speed in enterprise settings? Sobering findings, also some actionable insights from this study.

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

Today’s presentation at the Major League Baseball event was super fun. It was also good to debate and discuss what sort of software tactics and AI strategies that teams of 5-20 engineers should embrace right now. Lots of opinions!

[article] How to Manage Context in AI Coding. It’s not just about cleverly-written prompts. How do we think about context? This post has some good advice for doing it well.

[article] Developers don’t care about Kubernetes clusters. That’s true. But they’re forced to when things go wrong even if the app is “correct.” I wonder if it’ll be less about abstractions and overlays, and more about using AI to troubleshoot when you don’t know all the k8s commands.

[blog] GKE: From containers to agents, the unified platform for every modern workload. With Kubecon going on this week, you’ll probably see a lot of Kubernetes. This post from Drew is outstanding and shows all the progress being made.

[blog] Introducing Agent Sandbox: Strong guardrails for agentic AI on Kubernetes and GKE. This is a smart capability that’s now part of the core Kubernetes engine. It should reduce the risk/concern people have about agents running wild.

[blog] Boosting LLM Performance with Tiered KV Cache on Google Kubernetes Engine. These are some pretty wild performance improvements for those doing LLM inference on Kubernetes.

[article] Microsoft’s .NET 10 arrives with AI, runtime, and language improvements. Feels like a lowkey announcement set. I know I don’t watch this ecosystem as closely as before, but I haven’t noticed a ton of chatter about these major updates.

[blog] Integrating File Search with the Gemini CLI Extension. We just shipped this RAG-as-a-service feature for the Gemini API, and someone already built a cool open extension for the Gemini CLI. Amazing.

[blog] GitHub in 2025. Fascinating business unit to watch. Stephen has a good summary of the change in pace and tone evident at the recent GitHub Universe event.

[blog] Building AI Agents with the GO Agent Development Kit (ADK). I think Bill wins the award for “first piece I’ve seen written about the ADK Go” from a non-Googler.

[blog] Accelerate debugging with Crashlytics MCP Tools. Why go visit all these dedicated surfaces to do work if you can bring the data to wherever you want with MCP? I think we’re seeing a shift happen in real-time.

[blog] 100% coverage is not that trivial. Do you need complete coverage, or better coverage? Mark talks about the genuine work it takes to have test coverage that matters.

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

Was it a busy Monday for you? It was for me. Tomorrow I get to do a presentation at my favorite team’s ballpark as part of the MLB Tech Summit. So, that’s pretty awesome.

[blog] Predictions 2026: Software Development Goes From Jamming To A Full Orchestra. Diego has been close to this trend for a long time, so I listen to his perspective.

[blog] Build better software to build software better. Great post from the Slack team. If your build system is slow or painful, all the AI dev tools in the world won’t help you.

[blog] AlloyDB accelerates AI with automated vector indexing and embedding. This is kinda awesome. Auto embedding and auto indexing for your existing databases? That’s powerful.

[blog] Yes really, curl is still developed. Yes, this ubiquitous tool is still under active development. How? Why? Find out here.

[blog] Building AI Agents Visually with Google ADK Visual Agent Builder. Build some fairly sophisticated AI agents without slinging a lick of code? This new web builder included in our Agent Development Kit works pretty well.

[article] AI is all about inference now. Training was always going to be niche. Important, but not something everyone has to do. Inference is where it’s at. It’s good to have TPUs!

[article] Over one-third of companies plan to replace entry roles with AI, survey says. “Plan to” is different that “will do”, but nonetheless, we’re in an odd state.

[blog] Stop Vibe Coding Your Unit Tests. Real experience with these tools yields insights you won’t get from outside observers.

[blog] Go SDK Power-Up: ADK Support Arrives in MCP Toolbox. Build agents in Go, get access to a variety of data sources via MCP. Not a bad recipe.

[blog] The Go Ecosystem in 2025: Key Trends in Frameworks, Tools, and Developer Practices. Twice as many Go developers as five years ago? It’s a growing ecosystem, and here’s a look at what tools and tech matter.

[blog] Achieve better AI-powered code reviews using new memory capabilities on Gemini Code Assist. I like the idea of a code review agent that learns and adapts based on what your applied standards are. Check this out.

[blog] Terraform vs. Pulumi vs. Crossplane: Choosing the right IaC Tool for your platform. There are these, and I suspect another emerging paradigm for infrastructure management in the AI era.

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

Check out a handful of AI-related things today, including app building advice, new capabilities, and an architectural view of an AI platform. Have a great weekend!

[blog] Introducing the File Search Tool in Gemini API. While we offer an amazing input context window, you don’t want to keep shoving tons of content into each request. With this new Gemini API feature, we just made RAG absolutely trivial.

[blog] Google’s Gemini Models on Databricks. You can use all sorts of models with Databricks, but I’m glad everyone now has access to the best one 🙂

[article] Survey: Where AI Reduces Toil and Where It Still Falls Short. There’s still a lot of toil out there, even when AI is available. Tool sprawl also seems out of control!

[article] Sam Altman says OpenAI has $20B ARR and about $1.4 trillion in data center commitments. I’m no mathematician, but doesn’t seem to exactly add up. But hey, smarter people than me are don’t seem too worried about it.

[blog] Your First AI Application is Easier Than You Think. Yes it is. This blog post refers to a codelab that you can follow along with to build your confidence as an AI app builder.

[blog] Announcing User Simulation in ADK Evaluation. I really like this functionality. It’s baked into the Agent Development Kit, and lets you define a high level goal and use the LLM to dynamically produce the user side of the conversation to pursue that goal.

[blog] Prototypes vs Products. Different goals and mindset for each. Marty clarifies here and tries to keep product managers from embarrassing themselves.

[blog] Announcing the Agent Development Kit for Go: Build Powerful AI Agents with Your Favorite Languages. Go devs are getting some great frameworks for building AI apps and AI agents. Check this one out.

[article] The Production Generative AI Stack: Architecture and Components. Good look at an AI/ML stack. Not necessarily an AI agent or app stack, but some overlap.

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