Technology Overviews
Herdr: how to supervise coding agents
Herdr keeps coding agents visible and their terminals persistent. Here is how to evaluate its status signals, recovery behavior, and place in SRE work.
Commentary
Nate’s take on AI in production, reliability metrics, and how engineering teams work.
AIOps
What MTTD misses between the alert and the response
Separate detection from response, reconstruct the missing minutes, and find the delays that an improving average can conceal.
AIOps
What changes when an AI agent can write to production
Tool-using agents need bounded authority, observable actions, and a recovery path when a technically successful request produces the wrong result.
AIOps
AI token usage: plan for cost, latency, and context limits
Measure tokens per completed task, account for retries and tool output, and preserve the evidence an operational assistant needs.
AIOps
GPU capacity depends on power and cooling
When inference slows without obvious application errors, test physical constraints alongside queueing, workload changes, and software regressions.
AIOps
Evaluate Claude Opus 4.6 for operational work
Test evidence retrieval, long-session consistency, tool boundaries, and cost before letting a model influence production changes.
AIOps
Agent skills for SRE: write the execution contract
Define inputs, permissions, idempotency, verification, and stop conditions for one operational capability before expanding its authority.
AIOps
From AIOps signals to agent actions: design the handoff
Decide which workflow deserves an agent, where a fixed automation is sufficient, and how to measure the work left for responders.
AIOps
Measure on-call load before the rotation becomes unsustainable
Count interruptions, overnight disruption, escalation work, and the unfinished follow-up that page totals leave out.
AIOps
What AIOps alert correlation can hide
Evaluate AIOps grouping by detection coverage, investigation effort, and recoverable mistakes, not alert reduction alone.
AIOps
Release gates that hold up under incident pressure
Turn reliability policy into a release decision with fresh evidence, limited exceptions, and a clear path to resuming normal changes.
AIOps
NetApp and NVIDIA: evaluate the storage path behind AI workloads
Read validated architectures as a starting point for workload, recovery, and support testing, not a promise of automatic reliability.