{
  "id": 9092326,
  "title": "Observability in Microsoft Foundry: Tracing Agent Runs, Continuous Evaluation, and the OpenTelemetry Data Plane",
  "url": "https://urgent.news/2026/09/22/observability-in-microsoft-foundry-tracing-agent-runs-continuous",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-22T05:39:35.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/monuminu/observability-in-microsoft-foundry-tracing-agent-runs-continuous-evaluation-and-the-4gp"
  },
  "original_language": "en",
  "account": "This article explores the observability features of Microsoft Foundry, specifically focusing on how it captures and queries the execution details of agent runs using OpenTelemetry. Agents in Foundry can involve multiple operations such as model calls, tool invocations, retrieval queries, and other span-level tasks which can all have varying latency, token costs, failure modes, and error introduction points. Without proper tracing, debugging such agents becomes a tedious process of searching through logs and making educated guesses.\n\nMicrosoft Foundry utilizes OpenTelemetry, a CNCF standard for distributed tracing, metrics, and logs, to implement its tracing model. In this model, a Trace represents the entire journey of a single request through the system, uniquely identified by a trace_id. A Span is a single unit of work within a trace, like an LLM call, tool invocation, or retrieval query. Spans have attributes such as model name, token counts, tool name, and more, which are populated using the OpenTelemetry GenAI semantic conventions. This ensures that traces generated from different GenAI frameworks can be rendered uniformly across tooling.\n\nTraces in Foundry are exported via a trace exporter to Azure Monitor Application Insights, which acts as the single source of truth for observability data. This means Foundry doesn't maintain a separate proprietary trace store; instead, it leverages the existing Application Insights infrastructure, benefiting from its mature tooling, familiar query language (KQL), and existing security and cost considerations. The Foundry portal provides a read-through view of this data, eliminating the need for data duplication.\n\nThe article delves into how tracing works at runtime, setting up traces both server-side and client-side, and reading traces through the waterfall view. It also discusses continuous evaluation, multi-agent tracing, and the importance of security, cost, and common pitfalls in implementing tracing. Overall, it highlights the architectural decisions behind tracing in Foundry and provides practical recommendations for effective observability implementation.",
  "summary": "Day 10 of the Microsoft Foundry 100 Days / 100 Blogs series. You shipped an agent. It calls a model, invokes two tools, retrieves a few documents, and returns an answer. It works in your dev loop. Three weeks later, a support ticket lands on your desk: \"the assistant gave a wrong price for SKU-4471.\" You have no idea which of the six internal steps produced that number, whether the tool returned…",
  "key_points": [
    "Microsoft Foundry uses OpenTelemetry for distributed tracing, metrics, and logs.",
    "Traces represent a single request's journey through the system, identified by a traceid.",
    "Foundry exports traces to Azure Monitor Application Insights for unified observability."
  ],
  "editors_take": "Microsoft Foundry's integration with OpenTelemetry enables uniform tracing and observability across GenAI frameworks, leveraging Azure Monitor Application Insights for streamlined debugging and analysis.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}