Category: Daily Reading List

I lead a group of “young entrepreneurs” that meet every other week, and today we talked about improving our ability to ask better questions to ourselves and the people around us. It’s definitely something I’m working on! Have a great weekend.

[blog] I miss thinking hard. Yes, it’s gotten easy to get “answers” to questions quickly and skip the deep thinking. But that’s also on us. Are you making time? Allowing yourself to be bored and let your mind wander? Or are you occupying every moment with stimuli?

[blog] How I coded a Rails 8 CFP app in 30m with Antigravity. Just build apps that help you do things. Here’s a good case of saving a lot of manual work by building an app for a particular scenario.

[blog] My AI Adoption Journey. Authentic and helpful story from Mitchell here. Read it to see his journey with AI tools and what he learned along the way.

[article] Beyond Pilot Purgatory. Why do AI pilot projects fail? Why do many pilot projects fail? From what I’ve seen, and what’s called out here, it’s because the work is too isolated.

[blog] An Update on Heroku. It’s been heading this way, but still a bummer to see an OG PaaS player basically shutting it down.

[article] Amazon and Google are winning the AI capex race — but what’s the prize? We’re absolutely plowing into CapEx. We don’t build unless there’s demand!

[blog] Getting Started with Gemini 3: Unlocking the Cloud with the Free Trial. We’ve trimmed the steps over the years, but it can still feel daunting. So I asked my team to clearly document what it takes so that you can get up and running quickly.

[blog] GitHub Actions Is Slowly Killing Your Engineering Team. No holding back here. The CI (and source code) space is so ripe for something better.

[blog] Latest Gemini and Nano Banana Enhancements in LangChain4j. These are bigtime. Great upgrades for Java devs building smarter, more grounded agent apps.

[article] Where on Earth is vibe coding taking off the most? The Swiss and German folks drank the vibe coding Kool-Aid. Hungarians, not so much.

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

Another batch of articles today that impacted my thinking. Thanks to today’s reading list, I installed the MCP server for our Google Developer Knowledge API, realized I was thinking about MCP wrong, and felt grateful for the job changes I didn’t make.

[blog] Introducing the Developer Knowledge API and MCP Server. This is the best thing we’ll deliver this week. Developers (and AI tools) can now access a single source of truth for information about Google products.

[article] Three ways AI will change engineering practices. Don’t disagree with this. Have you planned for each?

[article] To Drive AI Adoption, Build Your Team’s Product Management Skills. It’s likely confirmation bias, but I’m noticing a LOT of conversation about the value of a product management discipline when embracing AI.

[blog] Context Management and MCP. Wow, my favorite post of the day. It definitely made me rethink some things token consumption and Skills.

[blog] Forget technical debt. The point here is that focusing purely on technical debt isn’t sufficient to fixing the problems in the system.

[article] What Happens When Technical Debt Vanishes? More thought experiments about technical debt! This was a compelling read.

[article] IT leaders grapple with AI agent sprawl. New source of debt, incoming! Companies need to get a handle on their agents, data, and integrations.

[blog] Easy FunctionGemma finetuning with Tunix on Google TPUs. I learned like four things from this post, and I’m tempted to actually run this example scenario myself!

[article] Anthropic releases Opus 4.6 with new ‘agent teams’. Is it model update season already? We’ve already made this one available on Vertex AI. OpenAI gave Anthropic about ten minutes in the spotlight.

[article] 4 self-contained databases for your apps. Which databases offer you a no-install binary that’s portable? I’m not sure I thought of this whole set.

[blog] Antigravity the Ralph Wiggum style. Turn your agent-building tool loose and let it relentless tackle a problem until it reaches the goal? It’s not for every case, but seeing this approach may spark ideas.

[article] Kilo CLI 1.0 brings open source vibe coding to your terminal with support for 500+ models. Interesting. These types of tools are getting so powerful.

[blog] I left FAANG for a startup and regretted it. We only seem to hear stories of raging successes after leaving a BIG TECH job. It’s useful to see a different perspective.

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

Today I was impressed by so many thought-provoking articles and blogs. Maybe the most all year so far!

[article] Google parent beats on revenue, projects significant AI spending increase. Wowza, Cloud had a remarkable quarter (and year). We’re doing a few things right over here.

[article] How should AI agents consume external data? It’s a good question and one I haven’t seen discussed much. Locked down data sources? APIs? Secured caches? Make sure you have some gateways in front.

[article] Leaders, gainers and unexpected winners in the Enterprise AI arms race. It’s early, of course, but there are signals about who the real players are. Interesting to see third party apps GROWING in the enterprise.

[lab] Build and Deploy to Google Cloud with Antigravity. I clicked through this new step-by-step tutorial. It’s an excellent way to see how AI can help with more than just generating new code.

[article] Shared memory is the missing layer in AI orchestration. This has been on my mind a lot. What type of shared knowledge/memory should be stored, who should access it, and how is it fed into tools and apps?

[blog] Self-Improving Coding Agents. Speaking of memory, this excellent post from Addy highlights the value of the “right” memories passed between iterations of agentic loops.

[blog] Advancing AI benchmarking with Game Arena. Why not use games to really test the decision-making of AI models?

[article] My View of Software Engineering Has Changed For Good. It’s unavoidable at this point. Fairly soon, if not already, it’s not going to make much sense to sling all the code yourself.

[article] Most People Can’t Vibe Code. Here’s How We Fix That. Even with millions of new “builders” out there, there’s still a lot of assumed knowledge about software that many don’t have. Do we need different surfaces and platforms than what we have now?

[blog] AI Slopageddon and the OSS Maintainers. With all these new builders, however, we’re breaking open source workflows and maintainer morale.

[blog] Researching Topics in the Age of AI — Rock-Solid Webhooks Case Study. Should we share our AI-driven research reports publicly? Does that contribute to the “slop” problem? Or when guided well, do these reports represent useful knowledge worth disseminating? I lean towards the latter.

[article] How Do Workers Develop Good Judgment in the AI Era? Great question. How do you get good judgement without experience? We have to redesign how we develop that judgement.

[blog] MCP Development with COBOL, Cloud Run, and Gemini CLI. The fact that you can even do this is the takeaway. Not that you should start building MCP servers with COBOL.

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

I’ve got a customer presentation tomorrow, and I love that deeply personalizing a demo now takes 30 minutes instead of hours. A couple of prompts to Google Antigravity, some light supervision, and I’ve got a nice little system deployed to the cloud.

[blog] Gemini Interactions API — One interface for models and agents. So much functionality hiding behind a single API endpoint! Mete does a great job explaining why Gemini model endpoints are capable of more than you think.

[blog] Automatic programming. If you’re in control and setting your software vision, it’s not vibe coding.

[article] Vercel rebuilt v0 to tackle the 90% problem: Connecting AI-generated code to existing production infrastructure, not prototypes. The vibe-to-production pipeline will be fascinating to watch in 2026. How do you build it right the first time, or harden on the way to deployment?

[blog] Beyond Prompt Engineering: Using Agent Skills in Gemini CLI. Excellent post that shows off a very important scenario: feeding up-to-date guidance and info to your agent.

[blog] Here’s how to tune into the Winter Olympics with Google. I’m more of a Summer Olympics person, but there’s always something compelling in any of these games. Following along on Youtube, Search, and Maps.

[blog] Is AI Disrupting Product Development? I liked the table in here that showed PM activities and where AI would have a big impact.

[article] 9 Trends Shaping Work in 2026 and Beyond. All these are quite interesting to me, and not the typical low-effort lists I see on this topic.

[blog] Predictive Analytics Reimagined with BigQuery Conversational Analytics. If you can access the data, you can now get answers from it. That’s a wild shift from even a few months ago.

[article] Snowflake debuts Cortex Code, an AI agent that understands enterprise data context. Sense-making products will be all the rage this year.

[article] OpenAI launches new macOS app for agentic coding. Makes sense. Everyone wants to have an IDE-like thing right now!

[blog] Hear more about interactive world models in our latest podcast. World models are WILD. Listen and watch this podcast episode to see what Project Genie is already capable of.

[blog] What We Got Right with Cloud Foundry. This platform was absolutely ahead of its time. Cloud Foundry got so many things right. And also adapted too slowly to what people wanted next!

[blog] Towards a science of scaling agent systems: When and why agent systems work. This links to an interesting paper that shows multi-agent systems performing well on parallel tasks, but degrading on sequential ones.

[blog] Cloud CISO Perspectives: 5 top CISO priorities in 2026. Good list and worthwhile areas to ensure your security team focuses on.

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

This week’s off to a hot start at work, and in the industry as a whole. It’s also earnings season across tech, so we can see who is making what type of real progress with AI.

[blog] Beyond Just Looking: Gemini 3 Now Has Agentic Vision. This is a bigger deal than we realize. Instead of “best guess” image processing, our model now does an agentic loop to truly understand an image.

[article] The Five Skills I Actually Use Every Day as an AI PM (and How You Can Too). Here’s a great challenge to PMs. If you’re not doing these types of activities, you’re going to quickly see people encroaching on your domain.

[blog] High-performance inference meets serverless compute with NVIDIA RTX PRO 6000 on Cloud Run. Truly impressive. Which other serverless stack is offering up to 44 vCPUs and 170+ GiB of RAM per instance and letting you run 70B parameter models on demand?

[blog] Summarizing Too Big for Context with MapReduce and LLMs. Smart approach from Wei here. If you’ve got a ton of input data, you can do a Map-Reduce-style exercise to distill the information.

[article] AWS’s inevitable destiny: becoming the next Lumen. It’s lucrative to be the backbone, but mindshare disappears.

[blog] The Rise of Coding Agent Orchestrators. Agent harnesses and orchestrators are going to have a big year. As will the management layers around them.

[blog] A Javelit Frontend for the Deep Research Agent. Ok, now I know what Javalit is, and why it’s great for building data apps without messing with the frontend.

[blog] Kubernetes Rolling Updates for Reliable Deployments. Solid post about how good Kubernetes has gotten at supporting rolling updates for your workloads.

[blog] LiteRT: The Universal Framework for On-Device AI. I don’t understand this space very well, but I read this to learn more. Getting cross-platform acceleration for AI workloads from a single framework is a good deal.

[article] Elon Musk’s SpaceX has acquired his AI company, xAI. The man goes big and plays to win, that’s for sure. The renewed investments in space are pretty exciting.

[article] Waymo raises $16B to scale robotaxi fleet internationally. Let’s go! Great to see this fantastic engineering get deployed more widely.

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

I haven’t figured out what topic I want to explore or which demo to build this weekend, but those autonomous agents hanging out at Moltbook may have already taken over the world by tomorrow anyway.

[blog] Performance shouldn’t be an afterthought: Hardening the AI-assisted SDLC. Great advice from Karl, and it shouldn’t be THAT difficult to ensure the AI tools make this a priority from the start of the project.

[blog] The 80% Problem in Agentic Coding. Very thought-provoking piece, and one that engineers (and their managers) should take to heart.

[blog] Spanner in 2025: Innovations powering intelligent, multi-model AI applications. The most powerful database service keeps getting better. Good roundup of last year’s upgrades.

[blog] Spring AI Agentic Patterns (Part 5): Building Interoperable Agents with the Agent2Agent (A2A) Protocol. I’m happy to see good support for A2A in the Spring ecosystem. When things like this happen, protocols take off.

[article] Get started with Angular: Introducing the modern reactive workflow. Good introduction, and modern AI tools make it much less scary to try it all out.

[blog] Beyond the Chatbot: A Blueprint for Trustable AI. This is a boring headline for a badass use case. Real time intelligence at a race track? Let’s go.

[article] AI is changing how work gets done. Here’s how CIOs can help. Are CIOs leading the AI change at companies or going with the flow?

[blog] Introducing Google Cloud Vertex AI Extensions for .NET. You’re not stuck with only one cloud option, C# devs. We’ve got new .NET 10 support in Cloud Run functions, and a new library to make it easier to add Gemini to your app.

[blog] Zero trust architecture for platform engineers: Securing modern developer platforms. Read this for a take on many of the key areas to focus on for a secure architecture that verifies everything.

[blog] I Tried Letting Antigravity Build An Agent For Me. Here’s What Actually Happened. I enjoy reading these. See where people stumbled, or found delight, is very helpful in knowing where to improves products/docs/messaging.

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

This morning, I read a blog post about a new product feature (the new conversational analytics baked into BigQuery), tried it out, and included it in a customer demo I did twenty minutes later. Gosh I love managed services that make that scenario possible.

[blog] Vibe coding needs git blame. This is a conversation worth having. I’m not sure I believe (currently) that prompts are merely intentions, not a build input. But none of this seems settled yet and we should keep figuring it out!

[blog] Accelerate GKE cluster autoscaling with faster concurrent node pool auto-creation. Wow, that’s a massive improvement in provisioning speed for Kubernetes clusters.

[blog] The Social Contract That Never Existed. I’m with Tim. Never got this naive, altruistic view of open source. Business models are under stress, not open source.

[blog] Introducing Conversational Analytics in BigQuery. Super cool feature that completely unlocks the ability for anyone to get insights from data.

[blog] Management as AI superpower. Fascinating post from Ethan that reiterates how important communication and management skills are for getting AI (agents) to do good work.

[blog] Project Genie: Experimenting with infinite, interactive worlds. Create, explore, and remix your own worlds. Just amazing. Available to the top tier of Google AI subscribers.

[blog] Flutter on Cloud Run: Full Stack Dart Architecture. There aren’t many languages you use for frontend AND backend, but Dart is one.

[blog] Building Semantic Search into Your AI Agents. Nice. Our MCP Toolbox for Databases now integrates embedding models into the workflow so that you can search using natural language that gets turned into vectors behind the scenes.

[article] Hands On Comparison: Building a Dynamic Web App in VS Code and Google Antigravity with Prompts Only. Solid evaluation, and I like that the author shares the detailed prompts so that anyone can recreate the experiment.

[article] Evals Are NOT All You Need. Evals are important, but there’s more to it. A process is needed to continuously cycle, not one-off checks.

[blog] Create your own AI language coach in 5 minutes. I feel like I’m too old to learn a new language, but maybe this would be a good test of what AI can do for me.

[blog] Software Engineering in 2026: Predictions from Leaders and Practitioners. We’re ending prediction season, but still good to see what a few smart folks have to say.

[blog] Cloud Run AI Agents: The Ultimate Guide to Serverless AI Deployment. It really is an outstanding service for running AI agents of all sorts, written in any language, and with virtually any resource demands.

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

Some cool AI updates from Google this week, including new treats in Chrome, an updated Gemini CLI, and Agentic Vision in Gemini 3 Flash.

[blog] The new era of browsing: Putting Gemini to work in Chrome. Each of these capabilities is genuinely useful. I like how Chrome embeds this into the experience, even for enterprise scenarios.

[blog] The AI Evolution of Graph Search at Netflix: From Structured Queries to Natural Language. Detailed post from Netflix about the text-to-query capability in their platform.

[paper] Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline. If you’ve got multiple agents that contribute to the same outcome and use the same underlying model, couldn’t you just solve the problem with a single agent? That’s what this paper explores.

[blog] Tailor Gemini CLI to your workflow with hooks. This is terrific. Intercept key stages of the agentic loop to insert logic that improves your security posture or performance.

[article] QCon chat: Is agentic AI killing continuous integration? Not killing, but definitely forcing everyone to rethink some key aspects of it.

[article] Google’s more affordable AI Plus plan rolls out to all markets, including the US. This is a great deal for people who want expansive, affordable access to great Google technologies.

[blog] The Mighty Metaphor. Are you providing your listening or reading audience with thoughtful metaphors that aid exploration?

[article] How should product managers decide which tasks to delegate to AI? I’m having a conversation tomorrow with a customer on this very topic, so this was well-timed!

[blog] Introducing Agentic Vision in Gemini 3 Flash. Treating AI vision as “active investigation” is super interesting. News here.

[article] Welcome to the last 18 months of labor-intentive services. The clock is ticking for service providers. Companies are better on software as services.

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

Great day here in Sunnyvale, with my “AI-first product lifecycle” talk + demo landing pretty well. I love hearing the questions from customers, as it calibrates me on what “real” people (not social media folks) care about.

[blog] Skills, Tools and MCPs – What’s The Difference? Well-written breakdown with easy to remember categories for these capabilities.

[blog] New developer tools for Google AI Pro and Ultra subscribers. Cloud credits are now included in our Google AI subscriptions.

[blog] the browser is the sandbox. Really good. Before reinventing the wheel, recognize that we have a hardened, widely-accessible sandbox right in front of us!

[blog] Beyond the “Happy Path”: Adding SpecKit to my Antigravity Workflow. Yes, tools like this can collapse steps and show eagerness to start building. It’s smart to slow down and make sure the product and engineering specs are solid.

[article] AI makes the database matter again. I’m not exactly sure how, but I do think databases will emerge as a bigger component of AI systems this year.

[blog] The Six Essential Protocols Powering the AI Agent Ecosystem. There’s probably more, but these are ones with significant mindshare already.

[article] When You Have to Assign Work No One Wants to Do. This gave me some tips for improving how I delegate or assign undesirable work.

[blog] BigQuery AI supports Gemini 3.0, simplified embedding generation and new similarity function. Easier to use and more powerful AI baked into the data warehouse? For data science and data analytics work, this is excellent.

[article] MCP shipped without authentication. Clawdbot shows why that’s a problem. Clawdbot is everywhere, although today they had to change their name to appease Anthropic. Either way, be careful out there and use good sandboxes.

[blog] Executable Markdown Files with gcli-mdrun & Gemini CLI. Wow, maybe Markdown + English is my programming preference this year! Super neat work from Guillaume that shows how you can go straight from intent to results.

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 San Jose in a few moments, and spent some free time this weekend building a demo that showcases the AI-first product development lifecycle. It goes from research to planning to building and deploying to operations. Figured I can’t talk about it if I hadn’t tried it myself!

[article] How MCP Server Help AI Act. Quick piece, but it’s a good reminder of what MCP can do for you. I used a couple of servers this past weekend to finish a project faster.

[blog] High-Risk, High-Scale: Guaranteeing Ad Budget Precision at 1 Million Events/Second. Every architecture won’t look like yours, but we can still learn from use cases that don’t directly apply to us.

[blog] Just for Fun: Migrating a legacy Spring Boot application with Conductor in Gemini CLI. Daniel takes a dusty Spring Boot app and shows us the flow to genuinely modernize it with our agentic CLI. Great flow.

[blog] 2026 Predictions from the Battery Team. Everybody’s got an angle, but I like VC predictions given how close they are to what’s relevant in the moment.

[blog] I’m addicted to being useful. Me too, but I’ve also found it’s important to be useful where needed, not everywhere. Sometimes I just need to listen, or watch things play out.

[blog] Improving workflow orchestration with Apache Airflow 3.1 in Cloud Composer. Other software, non-AI software, continues to hum along. The latest version of Airflow for data processing is available on Google Cloud.

[article] Engineering as Humanity’s Highest Achievement. I’m a huge nerd for giant engineering projects. I love them. Keep building!

[article] Pushing the Agentic Frontier with Ephemeral Messages. Very cool original idea from our Google Antigravity team. This seems to make a big difference in how well the IDE follows instructions over long conversations.

[article] 16 open source projects transforming AI and machine learning. Here’s a timely list, with a couple things I hadn’t heard of yet.

[blog] Beyond Buy vs Build: A new choice in the world of enterprise software. Lak’s “fourth path” is interesting. Will vertical AI startups generate custom software, saving customers from vibe coding custom SaaS?

[blog] Stop Calling It “Vibe Coding” — It’s Supervised Generation. The “let AI generate everything without watching” crowd is excited right now, but Tim provides a sensible reminder.

[article] Kubernetes 1.35 features that change Day 2 operations. What’s new for platform folks running Kubernetes? Jani covers it well here.

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