
AI logging: what to capture around a model request
Trace a model request through timings, retries, tool calls, configuration changes, and outcomes without collecting every message.
Read AI logging: what to capture around a model requestLog Mic Lab / Connected ideas
Stable fields make records easier to interpret together. These guides cover the event vocabulary, application boundaries, and file handling choices behind structured logging. They are useful when a human-readable message needs to become a consistent record that a collector or another team can understand.
Read the schema guide before choosing fields. Use the AI article to apply that discipline to model-driven operations, and the logfile guide to follow records through serialization and rotation. Field meaning and delivery behavior need to remain understandable at every step.
3 connected guides

Trace a model request through timings, retries, tool calls, configuration changes, and outcomes without collecting every message.
Read AI logging: what to capture around a model request
Design readable events with stable fields, clear outcomes, useful timing, and an investigation query to prove they work.
Read Structured logging: a practical guide to useful events
Build a logfile workflow that preserves event boundaries, follows rotation safely, and makes missing or repeated records visible.
Read JSON logfiles and rotation: a reliable collection workflowExplore a shared question across different kinds of logs. Each collection brings together relevant guides and a useful reading path.