Microsoft Reactor London

In the third session of our Python + Agents series, we’ll focus on two essential components of building reliable agents: observability and evaluation.

We’ll begin with observability, using OpenTelemetry to capture traces, metrics, and logs from agent actions. You'll learn how to instrument your agents and use a local Aspire dashboard to identify slowdowns and failures.

From there, we’ll explore how to evaluate agent behavior using the Azure AI Evaluation SDK. You’ll see how to define evaluation criteria, run automated assessments over a set of tasks, and analyze the results to measure accuracy, helpfulness, and task success.

By the end of the session, you’ll have practical tools and workflows for monitoring, measuring, and improving your agents—so they’re not just functional, but dependable and verifiably effective.

Discover how to run powerful AI models entirely on-device using Foundry Local. We’ll cover the architecture, how to compile Hugging Face models for local execution, and how to integrate everything with LangChain.js. You’ll also see a compact Android demo showcasing low-latency, offline AI experiences. By the end, you’ll know how to set up, optimize, and build local-first AI apps, and how to join the private preview to go deeper.

PARTNER SPOTLIGHT - Speed, Scale, and Control with Black Forest Labs Image Models in Microsoft Foundry
Stephen Batifol, Developer Advocate at Black Forest Labs, joins Model Mondays to show how teams use BFL’s generative image models on Microsoft Foundry to move from experimentation to real‑world creative workflows at scale with fewer touch‑ups, stronger brand fidelity, and state‑of‑the‑art image quality. This hands‑on session features a live demo and practical patterns for building scalable image pipelines, so you can ship complete creative campaigns in days, not weeks.

TECH SPOTLIGHT - Observability in Microsoft Foundry
Building trustworthy AI agents requires an end-to-end observability capability that lets us trace, monitor, and evaluate, agentic task execution at enterprise scale. Join us as we talk to Sebastian Kohlmeier (Principal PM, Core AI @Microsoft) about Observability capabilities in Microsoft Foundry - from tracing to evaluations, monitoring and more.