Agents crossed from answering to acting, reliability moved off the pager and into design and verification, and the outages that still hurt come from interactions nobody modelled. A trend brief built from 25 sources dated …
Why agent performance engineering lives in the harness, with a real repo update that adds per-step timing and workload estimates to trace summaries and run summaries.
A practical look at tracing, operator-facing observability, and trace-aware evals in the live harness-engineering demo after adding persisted trace summaries and lightweight eval fixtures.
Before handing the pager to an AI, we need a map of the territory. We survey the 2025–2026 SRE landscape to identify which domains are ready for autonomous agents and which remain firmly human.
