Had a demo call earlier today where the CLI wizard set the live demo up in under a minute. The user's reaction said it all. Very proud of the team for building something that actually works that smoothly. That kind of experience doesn't happen by accident.

I recently posted a screenshot of an AI-generated PR with 50k lines of changes. The comments exploded with opinions on PR best practices. Almost nobody stopped to ask whether the review process itself still makes sense. It's like walking past a burning building to debate the exit sign.

Finished doesn't mean closed. One of my favorite things about the Multiplayer web dashboard is that you can reopen any session and keep going in the same thread the agent used the first time.

This is a quote from Cat Wu, Head of Product, Claude Code, 👇 What makes this interesting to me, beyond practical advice, it’s what it signals about the maturity curve of working with AI.

If you’re using coding agents, your output numbers (epics completed, task throughput, PR merge rate, …) may look good right now. But those are not the metrics your manager is watching. Every single one of those numbers comes with an asterisk: production quality is declining.

Developers don't want more dashboards to stare at or more alerts to triage. They want the thing that broke, to fix itself. So we don't have to go through this flow of 👇 five tools, eleven steps and four hours just to fix a bug.

880+ engineering leaders were asked what challenges their organizations have experienced with AI in the past 6-12 months. 49% flagged security concerns. 48% are dealing with hallucinations. 23% reported an increased need for debugging.

The “10x engineer” was always a simplification and I was very pleased when it started to fade. Then AI coding tools arrived, and it came roaring back. Software engineering is a team sport. The engineers who create the most impact are the ones who multiply the capacity of the people around them.

Yes. Session-based, unsampled runtime data collection is very cool 😎

1 in 3 engineering managers is thinking about going back to IC. 37% say their hands-on technical work has increased in the last 12 months. AI made building fast enough to compete with managing again. @leaddev.com latest report puts numbers on what a lot of us have been feeling.

The latest Jellyfish's AI Engineering Trends research shows token consumption climbing sharply, but PR revert rates remain roughly flat across all AI adoption tiers, hovering in the same 0.45%–0.65% band they were in a year ago. More tokens per developer hasn't bought fewer reverted PRs.👇

This meme is a lie and we all know it 👇 Human PR review was always a bottleneck. We merged things we hadn't fully read and shipped things we shouldn't have. The difference now is that coding agents made it worse with PR slop.

First time at #KCDNewYork. Great event, easy to meet people, fantastic food. Met @salaboy.com, newly elected CNCF TOC member and author of Platform Engineering on Kubernetes. Already at the top of my reading pile. See you at the next one. 🙌

Who wants to review this PR? 👇😅 PR reviews were already a known weak point in software development before AI coding agents arrived. They just made it impossible to ignore.

Every major model release makes the same point: the frontier keeps moving. Claude Fable 5 today. Something better in six months. The most underrated decision any engineering team makes right now: building AI workflows that are MODEL-AGNOSTIC.

Back in NY from #LDX3 London. 3 sessions in 2 days: AMA panel, a talk on why most MCP servers are collecting dust, and moderating a peer group. The questions after my talk made every hour of prep worth it. @leaddev.com sets the bar high for developer conferences!

It’s hard not to make the connection between between AI output quality and data input. The sooner the distinction between dashboard data and agent data becomes a first-class engineering concern the sooner coding agents will actually deliver on what everyone expects them to do.

“Shift left” has become one of those empty buzzwords that started as genuinely useful and has become misunderstood or misused to the point where it just creates more confusion. See 🧵for the most concrete damage “shift left” does IMO

Minneapolis last week. New York on June 9-10. I'll be presenting at DeveloperWeek a talk I've been wanting to give for a while: From Alert to Action: Redesigning Your Observability Stack for Agentic AI.

First time at the @cncf.io Observability Summit. First time speaking there too. Honestly, what a rush. I gave a talk on building MCP servers and shared some of the lessons we've learned building the @multiplayer.app debugging agent on top of #OpenTelemetry.

Your manager doesn't care how many PRs you opened this week. They care about this: (1) Change Failure Rate (CFR): the % of deployments that break something in production. Industry benchmark is 4%. Some teams using AI coding tools are now running at 6%, shipping 50% more defects than before.

According to the most recent Pragmatic Engineer survey, Staff+ engineers use agents regularly at a rate of 63.5%, outpacing regular engineers (49.7%), engineering managers (46.1%), and directors and VPs (51.9%).

Most engineering teams are using AI to write code faster than ever. But they are also shipping bugs with equal speed. Ultimately, the root cause is a data problem.

Everyone in the room nods when you say “garbage in, garbage out.” It’s the first thing developers say when you ask them about AI and data quality. It’s also, apparently, the last thing they think about when they connect their observability stack to a debugging agent.

Hot take for a room full of observability practitioners: Logs, traces, and metrics were designed for a world where humans wrote and reviewed every line of code. That world is gone. I'm speaking at @cncf.io's Observability Summit North America in Minneapolis on May 21–22.

Turns out “is that a problem?” has a pretty clear answer.

System-first o11y has its function, but more and more devs are realizing that effective debugging requires a session-first approach with a single timeline that correlates: • User interactions • Console errors • Network req/res • Backend traces and spans

This chart should scare you👇. 96% of developers don't fully trust AI-generated code, yet only 48% always review it before it ships. Sit with that for a second.

First time speaking at a @cncf.io event. If you're going to be in Minneapolis, let's connect. ☕️👇 My talk will be all about the hard lessons from moving an MCP server into production and how to design for AI agents and effective debugging. Full schedule: observabilitysummitna26.sched.com

If your team isn’t discussing Spec-Driven Development or how your design decisions are documented, versioned, and shared, you’re undermining your AI tooling strategy.