Start here
How OpenTelemetry connects a request across services
See how signals and context fit together.
Read the articleObservability
Connect telemetry to an operational question, then follow the evidence through an investigation.
Choose the first request path
A first distributed trace from request to background job
Scope an initial tracing exercise around a customer-critical path.
Read the guideRead the evidence carefully
Reading time, concurrency and gaps in a distributed trace
Understand what a trace includes and what it cannot establish.
Read the articlePreserve useful events
The path from a log event to an investigation
Choose logs that support investigation rather than simply increasing volume.
Read the articlePut it into practice
Related AI news
News ·
Apigee adds model and MCP tool performance dashboards
Apigee separates model latency and token use from MCP tool traffic. Tool filters narrow a slow-assistant investigation, while proxy policies determine which charts populate.
News ·
Google API Gateway adds streaming for LLM responses
Google API Gateway’s streaming preview delivers response chunks while a model is still generating. Creation-time settings and request deadlines shape the migration.
News ·
Google ends maintenance for legacy Monitoring and Logging agents
Standard maintenance has ended for Google’s legacy agents. Migration to Ops Agent changes some metric fields, including disk labels used by existing queries.
More on observability
Guide · 25 min read
Hermes Agent guide: what it is, when to use it, and how to get started
Understand Hermes Agent, its origins, models, memory and skills. Choose a setup, try two checkable examples, and learn where its limits matter.
Guide · 6 min read
Measuring retry amplification in AI agent workflows
Connect logical tasks to every model and tool attempt, then measure cost and latency per accepted outcome without hiding failed or unknown work.
Guide · 6 min read
Shadow-testing an AI log classifier before migration
Run a candidate log classifier beside the current route, preserve complete outcomes, and promote only the slices whose mistakes and review cost are understood.
Guide · 9 min read
Measuring streaming LLM latency from first text to completed work
A client-side SSE probe separates first answer text from normal completion. Fixed arrivals and outcome counts show whether a serving change delivers more useful answers.