News
OpenTelemetry’s Kubernetes milestone matters for AI agent tracing
The stable Kubernetes attributes processor helps connect AI-agent traces to their workloads. Check the metadata joins before upgrading.
Search articles
Search titles and article text.
News
Kubernetes Memory QoS: what AI inference teams should test
Memory QoS reaches beta in Kubernetes 1.37. For AI inference teams, the rollout question is how host-memory policy affects serving latency and neighboring workers.
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.
AIOps
Production agents: authorize the action, then verify the outcome
Define production-agent authority, reconcile uncertain writes, verify outcomes independently, and use an execution contract before expanding scope.
How-To
OpenTelemetry for SRE: connect the signals that explain a request
Understand instrumentation, context propagation, and the Collector, and why consistent telemetry still needs careful signal design.
How-To
Where SRE and platform engineering need an explicit handoff
A practical ownership model for shared platforms, service reliability, incident command, and the work that falls between teams.
How-To
Postmortem risk treatment: decide what the fix actually proved
Separate delivered postmortem actions from demonstrated risk reduction, close only tested scope, and record residual exposure with a treatment worksheet.
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.
How-To
Use the 5 Whys without forcing an incident into one cause
Follow evidence through technical failure and incident response, then test whether the proposed correction changes the mechanism.
AIOps
NotebookLM for SRE: build a source-backed incident dossier
Use a curated notebook to compare runbooks and incident evidence, while keeping citations, freshness, and operational authority in view.
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.