# Feed

Articles, talks, and writing about AI agents in production.

## 2026

- [The substitution myth & the tough spot it puts us in](https://www.adaptivecapacitylabs.com/2026/10/02/the-substitution-myth-the-tough-spot-it-puts-us-in/) - John Allspaw, adaptivecapacitylabs.com, 2026-10-02
- [Can Claude Fix Itself? Using LLMs for Incident Response](https://www.infoq.com/presentations/claude-sre-incidents/) - Alex Palcuie, infoq.com, 2026-08-26
- [There is more to code review than (automatable) detection](https://www.adaptivecapacitylabs.com/2026/08/24/there-is-more-to-code-review-than-automatable-detection/) - John Allspaw, adaptivecapacitylabs.com, 2026-08-24
- [Wild AI-related reliability incidents are coming](https://surfingcomplexity.blog/2026/08/22/wild-ai-related-reliability-incidents-are-coming/) - Lorin Hochstein, surfingcomplexity.blog, 2026-08-22
- ['My Boss Wants Me to Pick an AI SRE Tool': Q&A at Incident Fest (Adaptive Capacity Labs)](https://www.uptimelabs.io/articles/incident-response-ai-qa) - Sam Salter, uptimelabs.io, 2026-08-11
- [Control and complexity: tension in systems design](https://ferd.ca/control-and-complexity-tension-in-systems-design.html) - Fred Hebert, ferd.ca, 2026-08-10
- [Expertise Can't Be Automated: Why Resilience Still Needs Humans](https://resilienceinsoftware.org/news/11560646) - Courtney Nash, resilienceinsoftware.org, 2026-08-03
- [I am dreading our LLM-written incident report future](https://surfingcomplexity.blog/2026/06/19/i-am-dreading-our-llm-written-incident-report-future/) - Lorin Hochstein, surfingcomplexity.blog, 2026-06-19
- [AI demands more engineering discipline. Not less](https://charity.wtf/p/ai-demands-more-engineering-discipline) - Charity Majors, charity.wtf, 2026-06-15
- [An AI Agent Debugs a Postgres I/O Spike: Multixacts, SLRU Caches, and a Crisis It Invented](https://www.arthur.ai/blog/ai-sre-debugs-postgres-io-spike) - Ian McGraw, arthur.ai, 2026-06-15
- [The on-call cost of AI-generated code](https://greatcircle.com/blog/2026/06/09/on-call-cost-of-ai-generated-code/) - Brent Chapman, greatcircle.com, 2026-06-09
- [AI in SRE: How Google is Engineering the Future of Reliable Operations](https://sre.google/resources/practices-and-processes/ai-engineering-reliable-operations/) - Ioannis Papapanagiotou, Stevan Malesevic, Chris Heiser, Ruslan Meshenberg, sre.google, 2026-05-28
- [The Pulse: AI load breaks GitHub – why not other vendors?](https://blog.pragmaticengineer.com/the-pulse-ai-load-breaks-github/) - Gergely Orosz, blog.pragmaticengineer.com, 2026-05-07
- [It's time to be right.](https://brooker.co.za/blog/2026/04/30/be-right.html) - Marc Brooker, brooker.co.za, 2026-04-30
- [How we built a real-world evaluation platform for autonomous SRE agents at scale](https://www.datadoghq.com/blog/engineering/bits-ai-eval-platform/) - Benjamin Barton, datadoghq.com, 2026-04-07
- [Kelsey Hightower at KubeCon 2026: "Everyone is a junior engineer when it comes to AI"](https://thenewstack.io/hightower-ai-open-source-kubecon/) - Jennifer Riggins, thenewstack.io, 2026-03-30
- [Fixing Claude with Claude: Anthropic reports on AI SRE](https://www.theregister.com/software/2026/03/19/fixing-claude-with-claude-anthropic-reports-on-ai-sre/5224819) - Tim Anderson, theregister.com, 2026-03-19
- [After outages, Amazon to make senior engineers sign off on AI-assisted changes](https://arstechnica.com/ai/2026/03/after-outages-amazon-to-make-senior-engineers-sign-off-on-ai-assisted-changes/) - Rafe Rosner-Uddin, Financial Times, arstechnica.com, 2026-03-10
- [Why Your On-Call Engineer Is Your Most Expensive Bottleneck](https://medium.com/@pranavkumarshil/why-your-on-call-engineer-is-your-most-expensive-bottleneck-4bb00dff32eb) - Pranav Kumar Shil, medium.com, 2026-03-10
- [Your Data Is Made Powerful By Context (so stop destroying it already)](https://charity.wtf/p/your-data-is-made-powerful-by-context) - Charity Majors, charity.wtf, 2026-03-09
- [We Automated Everything Except Knowing What's Going On](https://eversole.dev/blog/we-automated-everything/) - Kenneth Eversole, eversole.dev, 2026-03-02
- [Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems](https://arxiv.org/abs/2603.00468) - Yilun Wang et al., arxiv.org, 2026-02-28
- [The naked truth about AI-assisted coding](https://krasimirtsonev.com/blog/article/the-naked-truth-about-ai-assisted-coding) - Krasimir Tsonev, krasimirtsonev.com, 2026-02-26
- [The Picture They Paint of You](https://ferd.ca/the-picture-they-paint-of-you.html) - Fred Hebert, ferd.ca, 2026-02-23
- [Building An Elite AI Engineering Culture In 2026](https://cjroth.com/blog/2026-02-18-building-an-elite-engineering-culture) - Chris Roth, cjroth.com, 2026-02-18
- [Lots of AI SRE, no AI incident management](https://surfingcomplexity.blog/2026/02/14/lots-of-ai-sre-no-ai-incident-management/) - Lorin Hochstein, surfingcomplexity.blog, 2026-02-14
- [Are bugs and incidents inevitable with AI coding agents?](https://stackoverflow.blog/2026/01/28/are-bugs-and-incidents-inevitable-with-ai-coding-agents/) - David Loker, stackoverflow.blog, 2026-01-28
- [Practical Considerations for AI Incident Reviews](https://fgj.codes/posts/ai-incident-reviews/) - Fischer, fgj.codes, 2026-01-25
- [Bring Back Ops Pride](https://charity.wtf/p/bring-back-ops-pride) - Charity Majors, charity.wtf, 2026-01-19
- [Software engineering when machine writes the code](https://www.shayon.dev/post/2026/19/software-engineering-when-the-machine-writes-code/) - Shayon Mukherjee, shayon.dev, 2026-01-19
- [Tribal Knowledge Kills On-Call](https://medium.com/@a_pomorska/tribal-knowledge-kills-on-call-574863bf3eaf) - Angelika Alashwah, medium.com, 2026-01-19
- [Human-Centred AI for SRE: Multi-Agent Incident Response without Losing Control](https://www.infoq.com/news/2026/01/opsworker-ai-sre/) - Matt Saunders, infoq.com, 2026-01-18
- [The Future of AI in SRE: Preventing Failures, Not Fixing Them](https://thenewstack.io/the-future-of-ai-in-sre-preventing-failures-not-fixing-them/) - Asaf Savich, thenewstack.io, 2026-01-17
- [How we built an AI SRE agent that investigates like a team of engineers](https://www.datadoghq.com/blog/building-bits-ai-sre/) - Daniel Shan, Tristan Ratchford, datadoghq.com, 2026-01-12
- [Software Acceleration and Desynchronization](https://ferd.ca/software-acceleration-and-desynchronization.html) - Fred Hebert, ferd.ca, 2026-01-05
- [Your AI SRE needs better observability, not bigger models](https://clickhouse.com/blog/ai-sre-observability-architecture) - Manveer Chawla, clickhouse.com, 2026-01-01
- [Building internal agents](https://lethain.com/agents-series/) - Will Larson, lethain.com, 2026-01-01

## 2025

- [AI and the ironies of automation - Part 2](https://www.ufried.com/blog/ironies_of_ai_2/) - Uwe Friedrichsen, ufried.com, 2025-12-12
- [Facilitating AI adoption at Imprint](https://lethain.com/company-ai-adoption/) - Will Larson, lethain.com, 2025-12-07
- [AI and the ironies of automation - Part 1](https://www.ufried.com/blog/ironies_of_ai_1/) - Uwe Friedrichsen, ufried.com, 2025-11-21
- [Notes from the 2025 'AI Agents in Production' Conference](https://markptorres.com/ai_workflows/2025-11-18-ai-agents-in-production-conference-notes) - Mark Torres, markptorres.com, 2025-11-18
- [From 4 Hours to 8 Minutes with AI Agents That Transform SRE Incident Response](https://www.usenix.org/conference/srecon25emea/presentation/jausovec) - Peter Jausovec, usenix.org, 2025-10-08
- [Ongoing Tradeoffs, and Incidents as Landmarks](https://ferd.ca/ongoing-tradeoffs-and-incidents-as-landmarks.html) - Fred Hebert, ferd.ca, 2025-09-20
- [Stop Building AI Tools Backwards](https://hazelweakly.me/blog/stop-building-ai-tools-backwards/) - Hazel Weakly, hazelweakly.me, 2025-05-16
- [SREcon25 Americas - “On-Call Is Ruining My Life” and Other Tales about Holding the Pager as an SRE](https://www.youtube.com/watch?v=NWcXm9wnH-U) - Cory Watson, youtube.com, 2025-04-21
- [Another observability 3.0 appears on the horizon](https://charity.wtf/p/another-observability-3-0-appears-on-the-horizon) - Charity Majors, charity.wtf, 2025-03-24
- [AI: Where in the Loop Should Humans Go?](https://ferd.ca/ai-where-in-the-loop-should-humans-go.html) - Fred Hebert, ferd.ca, 2025-03-07
- [What Progress In Learning From Incidents Actually Looks Like](https://www.adaptivecapacitylabs.com/2025/02/28/what-progress-in-learning-from-incidents-actually-looks-like/) - John Allspaw, adaptivecapacitylabs.com, 2025-02-28
- [Observability: the present and future, with Charity Majors](https://newsletter.pragmaticengineer.com/p/observability-the-present-and-future) - Gergely Orosz, newsletter.pragmaticengineer.com, 2025-01-22

## 2024

- [End-of-Year Observability Retrospective with Charity Majors](https://horovits.medium.com/end-of-year-observability-retrospective-with-charity-majors-94f80fff77e8) - Dotan Horovits, medium.com, 2024-12-22
- [LLMs won't save us](https://blog.relyabilit.ie/llms-wont-save-us/) - Niall Murphy, blog.relyabilit.ie, 2024-12-12
- [Learning from Major Incidents: The Opportunities We're Missing](https://www.pagerduty.com/blog/incident-management-response/learning-from-major-incidents-the-opportunities-were-missing/) - Nora Jones, pagerduty.com, 2024-07-22
- [Leveraging AI for efficient incident response](https://engineering.fb.com/2024/06/24/data-infrastructure/leveraging-ai-for-efficient-incident-response/) - Diana Hsu, Michael Neu, Mohamed Farrag, Rahul Kindi, engineering.fb.com, 2024-06-24
- [Generative AI is not going to build your engineering team for you](https://charity.wtf/p/generative-ai-is-not-going-to-build-your-engineering-team-for-you) - Charity Majors, charity.wtf, 2024-06-10
- [Alert on symptoms, not causes](https://varoa.net/2024/03/06/alert-on-symptoms-not-causes.html) - Galo Navarro, varoa.net, 2024-03-06