Feed
Articles, talks, and writing about AI agents in production.
2026
The substitution myth & the tough spot it puts us in Oct 2
Can Claude Fix Itself? Using LLMs for Incident Response Aug 26
There is more to code review than (automatable) detection Aug 24
Wild AI-related reliability incidents are coming Aug 22
'My Boss Wants Me to Pick an AI SRE Tool': Q&A at Incident Fest (Adaptive Capacity Labs) Aug 11
Control and complexity: tension in systems design Aug 10
Expertise Can't Be Automated: Why Resilience Still Needs Humans Aug 3
I am dreading our LLM-written incident report future Jun 19
AI demands more engineering discipline. Not less Jun 15
An AI Agent Debugs a Postgres I/O Spike: Multixacts, SLRU Caches, and a Crisis It Invented Jun 15
The on-call cost of AI-generated code Jun 9
AI in SRE: How Google is Engineering the Future of Reliable Operations May 28
The Pulse: AI load breaks GitHub – why not other vendors? May 7
It's time to be right. Apr 30
How we built a real-world evaluation platform for autonomous SRE agents at scale Apr 7
Kelsey Hightower at KubeCon 2026: "Everyone is a junior engineer when it comes to AI" Mar 30
Fixing Claude with Claude: Anthropic reports on AI SRE Mar 19
After outages, Amazon to make senior engineers sign off on AI-assisted changes Mar 10
Why Your On-Call Engineer Is Your Most Expensive Bottleneck Mar 10
Your Data Is Made Powerful By Context (so stop destroying it already) Mar 9
We Automated Everything Except Knowing What's Going On Mar 2
Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems Feb 28
The naked truth about AI-assisted coding Feb 26
The Picture They Paint of You Feb 23
Building An Elite AI Engineering Culture In 2026 Feb 18
Lots of AI SRE, no AI incident management Feb 14
Are bugs and incidents inevitable with AI coding agents? Jan 28
Practical Considerations for AI Incident Reviews Jan 25
Bring Back Ops Pride Jan 19
Software engineering when machine writes the code Jan 19
Tribal Knowledge Kills On-Call Jan 19
Human-Centred AI for SRE: Multi-Agent Incident Response without Losing Control Jan 18
The Future of AI in SRE: Preventing Failures, Not Fixing Them Jan 17
How we built an AI SRE agent that investigates like a team of engineers Jan 12
Software Acceleration and Desynchronization Jan 5
Your AI SRE needs better observability, not bigger models Jan 1
Building internal agents Jan 1
2025
AI and the ironies of automation - Part 2 Dec 12
Facilitating AI adoption at Imprint Dec 7
AI and the ironies of automation - Part 1 Nov 21
Notes from the 2025 'AI Agents in Production' Conference Nov 18
From 4 Hours to 8 Minutes with AI Agents That Transform SRE Incident Response Oct 8
Ongoing Tradeoffs, and Incidents as Landmarks Sep 20
Stop Building AI Tools Backwards May 16
SREcon25 Americas - “On-Call Is Ruining My Life” and Other Tales about Holding the Pager as an SRE Apr 21
Another observability 3.0 appears on the horizon Mar 24
AI: Where in the Loop Should Humans Go? Mar 7
What Progress In Learning From Incidents Actually Looks Like Feb 28
Observability: the present and future, with Charity Majors Jan 22
2024
End-of-Year Observability Retrospective with Charity Majors Dec 22
LLMs won't save us Dec 12
Learning from Major Incidents: The Opportunities We're Missing Jul 22
Leveraging AI for efficient incident response Jun 24
Generative AI is not going to build your engineering team for you Jun 10
Alert on symptoms, not causes Mar 6