AI Logging guides.

This collection focuses on the application boundaries around model requests: correlation, attempt handling, observed duration, outcomes, and deliberately scoped content capture. Begin with the AI logging article, then use the linked token guide for usage reconciliation. The emphasis is on an inspectable application workflow with clear field meanings and limits, rather than a promise that more telemetry explains every model output.

AI logging gives model-driven workflows an inspectable history. Follow application operations, distinguish attempts from completed work, and keep sensitive content out of routine telemetry unless there is a defined reason to capture it. Visit the AI Logging topic guide for the starting questions, a short checklist, and the scope of this collection.