Observe AI agents that run on Azure OpenAI.
Your agent calls Azure OpenAI deployments. Trefur captures each invocation as a span on the agent trace — same shape as OpenAI direct, Anthropic, Bedrock, and Gemini — with deployment, region, tokens, cost, and any tool calls.
What you see.
Why it matters.
For engineers
Drop in the Trefur SDK. The Azure OpenAI client is auto-instrumented. Existing code keeps working; spans appear on the agent trace immediately.
For platform teams
Roll up Azure OpenAI usage per deployment, per resource group, per region. One trace shape across Azure, OpenAI direct, Anthropic, and Bedrock so dashboards keep working through vendor swaps.
For business operators
Know which workflows depend on Azure deployments and what they cost. Catch deployment changes that quietly raise cost-per-run.
For SRE
Azure throttling and content-filter blocks show up on the span. Envelope alerts catch retry-rate spikes per agent and route to oncall with the trace attached.
How it works.
Your agent calls Azure OpenAI through the official SDK or the REST endpoints. The Trefur SDK wraps the Azure client and emits an LLM span per chat completion, embedding, or assistants call. Spans use the OpenTelemetry GenAI shape so they line up with calls from any other vendor. The collector can run inside your network for on-network capture and configurable redaction.
See what your Azure OpenAI agents are actually doing.
Free tier. No card required. First trace in under five minutes.