Request-level observability in Foundry that must be switched on first. Each request becomes an OpenTelemetry trace in the connected Application Insights resource, showing latency, token usage, tool calls, inputs and outputs.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Tracing (Foundry) in context, with comparison tables and the common traps.
Terms in this definition
- FIRST
A DAX function available only inside visual calculations. It fetches the value at the start of one axis of the visual's matrix, which makes it handy for comparing each point with the first; its opposite is LAST.
- OpenTelemetry
Vendor-neutral standard for logs, metrics and traces. Application Insights in Azure Monitor and Foundry tracing both build on it, GenAI semantic conventions included.
- Application Insights
APM service within Azure Monitor providing application telemetry, availability tests, usage analytics and Application Map. Data from workspace-based instances lives in Log Analytics.
- Token
The unit of text an LLM works with, which may be a word, part of a word or punctuation. Billing, limits and context windows are all counted in these units.
- total_tokens
The usage field that sums prompt_tokens and completion_tokens, for example 37 + 86 = 123. Billing applies to both kinds of token.
- Chat message roles
Labels on chat messages: instructions go under system, the person's input under user, the model's previous answers under assistant, and results returned by a called tool under tool (or function).