🤖
AI-Assisted Incident Response
How leading teams are using LLMs to triage, route, and resolve incidents in minutes instead of hours.
Three days of deep-dive talks, hands-on workshops and frank conversation with the engineers redefining how the world stays online — with AI, eBPF, OpenTelemetry and platform thinking at the centre.
The Programme
From AI-powered incident response to kernel-level observability, these are the conversations shaping reliability practice in 2026.
How leading teams are using LLMs to triage, route, and resolve incidents in minutes instead of hours.
Generating actionable runbooks and blameless postmortems with large language models, and keeping them accurate over time.
Zero-instrumentation profiling and tracing at the kernel level — what eBPF unlocks for SREs in 2026.
Battle-tested patterns for collecting, sampling, and routing telemetry at millions of spans per second.
Building internal developer platforms that raise the floor without raising the cognitive load.
Designing error budgets that actually drive decisions, and chaos programmes that find real weaknesses.
Three Days
Tracks colour-coded by theme. All times shown in BST.
Registration
Three days, three keynotes, eighteen talks, and a community of engineers who care about uptime as much as you do.