🏈 SREs don’t need AI that tries to carry the ball. They need a teammate who clears the path. When an AI tool tries to “run the play” by rolling back production without approval, engineers are left wondering: did it actually fix the problem, or just create a bigger one? During

🎈 99 Luftballons… er, uh, blog posts. Joey Gonzalez and Vikram Sreekanti have been writing about AI for 2 years. What did they learn? They share their top insights in this retrospective post. Do you have some time for me? Then I’ll sing you a song… about ninety-nine AI blog posts.

How MCP accelerates AI-to-AI interaction: The next phase of AI UX is APIs and protocols that let agents talk to your product and to each other. In Ep 42 of LLMs on the Run, Professor Joseph Gonzalez (Joey) explains why: ✅ MCP and A-to-A protocols will become the real “UX” for

🗓️ ICYMI. Run of the Week | Sep 29, 2025 Last week at RunLLM: blogs, features, and hot takes worth a second look. 🎈 The AI Frontier: Lessons from 99 Blog Posts German musical artist, Nena, had a hit song in 1983 called 99 Red Balloons. This is like that but totally different.

🔥 Never let a good incident go to waste. Most teams fight the fire, fix the issue… and lose the lessons. Runbooks decay. Postmortems get skipped. Building institutional knowledge fails. AI can change that. By capturing the actual steps engineers take during incidents,

🛡️ You can’t build a moat with AI models alone. Differentiation doesn’t come from clever prompts or picking the “right” LLM — those advantages disappear fast.The real moat? Your data and how you engineer it. As LLMs get better (and more commoditized), the teams that win will be

What if your support team could solve customer or reliability problems before they even happened? That’s the future Professor Joseph Gonzalez (Joey) explores in Ep 44 of LLMs on the Run. He describes how AI Support Engineers — and now AI Site Reliability Engineers — could

🗓️ ICYMI: Run of the Week | Oct 6, 2025 AI Predictions + Incident Intelligence + Celebrating 100 Posts 🎉 The AI Frontier: Our 100th Post Makes Bold AI Predictions After 100 posts, Joey Gonzalez and Vikram Sreekanti have earned the right to speculate. Enterprise adoption, platform

Every SRE team has a few engineers who just know. They seem to spot root causes before they even open a dashboard. But when they leave, the know-how leaves with them. That’s why teams build runbooks and documentation—but keeping them current is a Sisyphean task. As systems

What's interesting about the Dev Day announcements this week is that... they really weren't for developers. OpenAI has very quickly transformed itself into a consumer company in a way that we honestly didn't expect. Joey Gonzalez and I break down the latest announcements and who

🗓️ ICYMI: Run of the Week | Oct 13, 2025 OpenAI vs Anthropic + Tribal Knowledge + Dumb questions 🛍️ The AI Frontier: Is OpenAI a Consumer Company Now? Joey Gonzalez and Vikram Sreekanti observe that a year ago, OpenAI seemed built for developers while Anthropic focused on end users.

🙀 You know what sucks worse than having an outage? When your customers have to tell you it’s happening. Dashboards are green. No alerts are firing. And yet your customers — and your colleagues — are lighting you up. Can AI-powered detection systems catch what everyone else

Over the last year, AI companies have either moved towards building broader products or narrower ones. Which one's better? Joey Gonzalez and I have some opinions: The post this week explores why narrowly-scoped agents are beginning to deliver more value than generic platforms 👇

Your SRE team is about to go bankrupt—and AI coding tools are why. Every CTO celebrates the productivity gains: 2× throughput, 50% faster development. But AI-generated code enters production with zero ownership. Reading code is not the same as writing it. The hidden costs: ✅

What happens when your customers aren’t people, but other AI? The next generation of successful software won’t just use AI. It will serve it. In Ep 48 of LLMs on the Run, Joey Gonzalez (Joey) looks at what happens when AI becomes both the provider and the customer — and how that

For the most part, everyone's use of AI today is synchronous and interactive... but it doesn't have to be that. As agents proliferate, we'll see more and more agents working in the background, doing things for us that we didn't want to bother doing ourselves. The most obvious

🗓️ ICYMI: Run of the Week | Oct 27, 2025 AI Tech Debt + AI Code vs Reliability + AI for AI 📌 Can AI Agents Clean Up Our Tech Debt? As soon as we learn to build better software, we create debt. And not only in code, but also knowledge, processes, and communication. Vikram

"Build opinionated products" is not new advice, but it's more important than ever. If you're not careful, your agents can be everything to everyone. That might sound wonderful at first, but it's going to cause you headaches later. Here's why 👇

Trillion dollar data center buildouts are all the rage. Why is all of this kicking off at once? The infrastructure investment we're seeing tells us a lot about the future of inference and the economics of intelligence. Joey Gonzalez and I break down why intelligence might not be

Looking back on 2025, lots of things changed in AI, but relatively little shocked us. AI will change a lot, but it might turn out to be a regular, old platform shift (like cloud, mobile, etc.). Joey Gonzalez and I on why 👇