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] 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!
[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] 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] 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.
[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.
You’ll find a lot of fun reads on this Friday. I’ve got a couple of projects in mind for the weekend as I prepare for a handful of in-person customer presentations next week in Sunnyvale.
[blog] Bring Back Ops Pride. Must-read piece, as always, from Charity. Ops != “toil” and the ability to build, run, and protect core services is superstar work.
[blog] Agent Skills vs. Rules vs. Commands. I do believe this will get simpler, or exposed in higher order abstractions. But for now, learn the hard way.
[blog] MCP, Skills, and Agents. So good. Skills don’t “kill” MCP. Poorly done MCP is bad either way, and done well it’s useful. Lots of other great insights here.
[article] Best Practices for Claude Code. I’d like you to use the Gemini CLI, but that doesn’t mean we can’t use and learn from other tools too.
[blog] Results from the 2025 Go Developer Survey. Transparent, interesting data from this team, as always. What are Go devs doing, what are their concerns, and how they tackling AI? Get the answers here.
[blog] Review of Google Antigravity for Building Jira Apps. Solid real-world example, with highlights and gotchas. I like that once he had the right app (and corresponding specs) built, he deleted all the code to see if Antigravity could build it correctly just from the spec.
Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below:
It’s been a fourteen meeting day (with one more this evening) so my battery is drained. On the plus side, lots of great things going on around here.
[article] The Palantirization of everything. Many companies are enamored with high-touch, forward-deployed engineers. But is that a playbook others can copy?
[blog] Architecture for Disposable Systems. I like the thought exercise behind this idea. What if that app doesn’t need careful engineering?
[blog] Code Is Cheap Now. Software Isn’t. No barrier to entry, and virtually no cost to produce code. But software is still expensive, and doing it with taste and timing will remain a differentiator.
[blog] Agent Psychosis: Are We Going Insane? Armin wonders if we’re losing the plot, getting addicted to prompts, or need better tools as we figure out the new norms of software engineering.
[blog] A Brief History of Ralph. A few months ago, “Ralph Wiggum” was just a sweet idiot kid from The Simpsons. Now? It’s a hot AI engineering approach.
[blog] AI Agent Engineering in Go with the Google ADK. My product area is actively working to make Go the best language for devs building AI apps. See here how to build out some AI agents in Go.
Happy pretend Monday. Since yesterday was a US holiday, I’ll be thrown off all week. But, today was maybe my favorite reading list of the year so far. Some really fun items.
[blog] How Our Engineering Team Uses AI. Here’s how a startup engineering team uses AI for understanding codebases, explore ideas, write scripts, and outsource toil. They also call out where AI isn’t making a big difference.
[blog] How we built an AI-first culture at Ably. You might have to mandate it to force the habit change, but AI adoption often becomes organic once people see where the value is. This post offers good pillars for successful AI adoption.
[blog] Everything Becomes an Agent. Will every AI project, given enough time, converge on becoming an agent? Allen thinks so.
[report] State of MCP. I don’t think I’ve seen this much data about MCP usage. Check it out for early signals on patterns, pain points, and value.
[blog] The Power of Constraints. Constraints are freeing. Some of the best people use their present limitations to do amazing things within those (often temporary) boundaries.
[article] Demystifying evals for AI agents. Anthropic put out some terrific content here that will put you in better shape when designing and running evaluations of your agents.
We’re only getting started with what you can build with agentic tools. Sure, vibe coding platforms like Lovable make it super simple to develop full-featured web apps. But developers are also building all sorts of software with AI products like Claude Code and Google Antigravity.
Antigravity doesn’t just plan wide-ranging work; it does it too!
Antigravity can do more than ship code and you don’t even have to leave your editor.
In this demo, the agent reads a blog post, extracts the core narrative, and builds a Google Slides deck from scratch, handling the research and initial build for you. pic.twitter.com/CB0S5JKP4M
Tweet from the Antigravity account showing a non-coding use case
Reading that tweet gave me an idea. Could I build out a complex database solution? Not an “app”, but the schema for a multi-tenant SaaS billing system? One that takes advantage of Antigravity’s browser use, builder tools, and CLI support?
Yes, yes I can. I took a single prompt to flex some of the best parts of this product, and, to generate an outcome in minutes that would have taken me hours or days to get right.
I started by opening an empty folder in Antigravity.
An empty Google Antigravity session
Here’s my prompt that took advantage of Antigravity’s unique surfaces:
I want to architect a professional-grade PostgreSQL schema for a multi-tenant SaaS billing system (think Stripe-lite).
Phase 1: Research & Best Practices Use the Antigravity Browser to research modern best practices for SaaS subscription modeling, focusing specifically on 'point-in-time' billing, handling plan upgrades/downgrades, and PostgreSQL indexing strategies for multi-tenant performance. Summarize your findings in a Research Artifact.
Phase 2: Schema Design Based on the research, generate a multi-file SQL project in the /schema directory. Include DDL for tables, constraints, and optimized indexes. Ensure you account for data isolation between tenants.
Phase 3: Verification & Load Testing Once the scripts are ready, use the Terminal to spin up a local PostgreSQL database. Apply the scripts and then write a Python script to generate 100 rows of synthetic billing data to verify the indexing strategy.
Requirements: Start by providing a high-level Implementation Plan and Task List. Wait for my approval before moving between phases.
Note that I’m using Antigravity’s “planning” mode (versus Fast action-oriented mode) and Gemini 3 Flash.
A few seconds after feeding that prompt into Antigravity, I got two artifacts to review. The first is a high-level task list.
Google Antigravity creating a task list for our database project
I also got an implementation plan. This listed objectives and steps for each phase of work. It also called out a verification approach. As you can see in the screenshot, I can comment on any step and refine the tasks or overall plan at any time.
An AI-generated implementation plan for the database project
I chose to proceed and let the agent get to work on phase 1. This was awesome to watch. Antigravity spun up a Chrome browser and began to quickly run Google searches and “read” the results.
A view of Antigravity’s browser use where it searched for web pages and browsed relevant sites
Once it decided which links it wanted to follow, Antigravity asked me for permission to navigate to specific web pages that provided more information on SaaS billing schemas.
Google Antigravity asking permission before browsing a web site
When the research phase finished, I had a research summary that summarized the architecture, patterns, and details that represented our solution. It also embedded a video overview of the agent’s search process. I never had this paper trail when I build software manually!
Research summary including a video capture of Antigravity’s browser search process
Note that Antigravity also kept my task list up to date. The first phase was all checked off.
Maintained task list
Because I was doing this all in one session, I added a note to the chat that indicated I was ready to proceed. If I had walked away and forgot where I was, I could always go into the Antigravity Agent Manager and see my open tasks in the Inbox.
Antigravity Agent Manager inbox where we can see actions needing our attention
It took less than 25 seconds for the next phase to complete. When it was over, I had a handful of SQL script files in the project folder.
Generated scripts for our database project
At this point, I could ask Google Antigravity to do another evaluation for completeness, or ask for detailed explanations of its decisions. I’m in control, and can intervene at any point to redirect the work or make sure I understand what’s happened so far.
But I was ready to keep going to phase 3 where we tested this schema with actual data. I gave the “ok” to proceed.
This was fun too! I relocated the agent terminal to my local terminal window so that I could see all the action happening. Notice here that Antigravity created seed data, a data generation script, and then started up my local PostgreSQL instance. It loaded the data in, and ran a handful of tests. All I did was watch!
Google Antigravity using terminal commands to test our database solution
That was it. When the process wrapped up, Antigravity generated a final Walkthrough artifact that explained what it did, and even offered a couple of possible next steps for my data architecture.
Complete walkthrough of how Google Antigravity built this solution
Is your mind swirling on use cases right now? Mine still is. Maybe infrastructure-as-code artifact generation based on analyzing your deployed architecture? Maybe create data pipelines or Kubernetes YAML? Use Google Antigravity to build apps, but don’t discount how powerful it is for any software solution.
[blog] How to write a good spec for AI agents. Goodness this is absolutely stuffed with useful information. Go through this and immediately up your game.
Do ever have those “perform research” days where you know your brain will be running a background thread even after you’re done working? I can sense it, after a day of investigating a handful of distinct areas.
[blog] Gemini introduces Personal Intelligence. When your AI assistant remembers its history with you, that’s helpful. When it “knows” your overall digital history, it becomes massively useful.
I talked too much today. Did a podcast episode with someone and was a guest at a fireside chat in our San Diego office. I try to listen more than I talk in 1:1s, so that balanced things out today a bit.
[blog] Your AI coding agents need a manager. You’ll see so much of this in 2026. We’re entering the phase of multiple agents working for you. Learn good communication skills, prioritization skills, and stay smart on the underlying tech.
[article] AI is rendering some IT skill sets obsolete. Some tech skills from 2010 are obsolete. Few things stay entirely static! But the pace may be accelerating for some skills that weren’t obviously open to replacement.
[blog] The Tool Bloat Epidemic. This post has a handful of solid suggestions for avoiding MCP tool bloat that eats your tokens and contributes to context rot.
Richard Seroter's Architecture Musings 