Developments that matter in production
What changed, how it works and what it means for the people running reliable systems.
6 stories · 1–6
How we reportApigee separates model latency and token use from MCP tool traffic. Tool filters narrow a slow-assistant investigation, while proxy policies determine which charts populate.
Background reading: ObservabilityGoogle API Gateway’s streaming preview delivers response chunks while a model is still generating. Creation-time settings and request deadlines shape the migration.
Background reading: Platform engineeringStandard maintenance has ended for Google’s legacy agents. Migration to Ops Agent changes some metric fields, including disk labels used by existing queries.
Background reading: ObservabilityCloudWatch Omni combines service discovery, agent evaluations, traces and natural-language queries. Its spaces retain account and Region scope, shaping cross-service investigations.
Background reading: ObservabilityKubernetes attributes connect agent calls to pods, workloads and paging routes. A processor migration can break those connections while telemetry still flows.
Background reading: ObservabilitySplunk’s September releases combine agent traces, evaluations and token-cost monitoring. A rejected incident summary shows how retries and human corrections affect the apparent saving.
Background reading: Observability