Content by Lee Stott (17)

Lee Stott wraps up the FibreOps series with a practical look at running autonomous agent systems in production: adding hands-free spoken updates via Azure AI Voice Live, and building an observability stack with OpenTelemetry and Application Insights so agent decisions can be traced, evaluated, and audited.

Lee Stott explains how to take agents from development to production in Microsoft Foundry Agent Service, covering Hosted Agents (container + manifest deployment), the Agent Optimizer, deterministic Routines, Memory, Toolboxes, and end-to-end tracing with OpenTelemetry and Application Insights.

Lee Stott continues the FibreOps series with a hands-on look at building role-specialised autonomous agents using the Microsoft Agent Framework, including tool design patterns, an orchestrator pipeline, and a GitHub Copilot SDK adapter for conversational control of the system.

Lee Stott introduces Microsoft’s end-to-end agent platform (now GA) using the FibreOps reference implementation: build agents with the Microsoft Agent Framework and GitHub Copilot SDK, run them as hosted agents in Microsoft Foundry Agent Service, and distribute them to Teams and Microsoft 365 Copilot, with evaluation, routines, memory, and observability.

Lee Stott walks through an end-to-end, production-minded approach for taking a multi-agent system from local development into Microsoft Foundry Agent Service, then distributing it to users in Microsoft Teams. The guide focuses on identity, governance, observability, and repeatable deployment using the FibreOps reference implementation.

Lee Stott explains why the Model Context Protocol (MCP) is becoming the standard way AI agents connect to tools and data, then shows minimal runnable MCP server examples in Python and TypeScript plus practical guidance for VS Code hosting, security, and production operations.

Lee Stott invites AI engineers to a Microsoft Foundry Discord round table on using the Browser Automation Tool (BAT) to let agents drive real browser workflows via Playwright Workspaces, with a focus on setup basics, practical use cases, and the guardrails needed for responsible, auditable automation.

Lee Stott invites AI engineers to a Microsoft Foundry Discord round table on scaling agent apps beyond demos, focusing on how Foundry Toolbox, Skills, and Tool Search reduce tool sprawl, prompt bloat, and auth plumbing by centralizing tools behind a governed MCP endpoint with runtime discovery.

Lee Stott tours Microsoft’s open-source course on taking AI agents from prototype to production using Microsoft Agent Framework and Microsoft Foundry, covering agent design, multi-agent orchestration, evaluation, deployment, data sovereignty, and tool governance with concrete commands and code patterns.

Lee Stott walks through a full “Multi‑Agent Dev Canvas” scenario for GitHub Copilot Canvas, showing how to decompose work, execute agent flows, validate with in-surface tests, inject failures, and evolve the design live (including GDPR/PII redaction) until the system meets its acceptance criteria.

Lee Stott explains what GitHub Copilot App Canvas is actually for: a development-time runtime where humans and AI agents can observe, steer, test, and evolve a running multi-agent system. The post walks through a real Canvas extension and the core building blocks needed to implement one.

Lee Stott explains the Model Context Protocol (MCP) and why it’s becoming a practical standard for connecting LLM apps to tools and data. The post highlights recent updates to Microsoft’s MCP for Beginners curriculum, including spec alignment, validated SDK samples, and a security-focused refresh with concrete fixes and audits.

Lee Stott shows how to provision the Azure infrastructure for Microsoft Foundry Hosted Agents using Terraform, including the Foundry Account and Project, an OpenAI model deployment, managed identity + RBAC, monitoring with Log Analytics/Application Insights, and a GitHub Actions workflow using OIDC for CI/CD.

Lee Stott lays out a practical GitOps approach for running Microsoft Foundry Hosted Agents in production, using GitHub as the source of truth and GitHub Actions/Tasks for validation, promotion gates, and rollback. It includes a reference architecture, repo layout, workflow examples, and security/observability guidance.

Lee Stott shows how to build a fully on-device voice assistant using Microsoft Foundry Local, combining Nemotron Speech Streaming for live transcription with a small local chat model. The post focuses on a practical FastAPI + browser pipeline, plus the SDK/version and streaming details needed to avoid deadlocks and “model not found” errors.

Lee Stott breaks down the Microsoft Foundry Agent Lab, a progressive set of nine Python demos that build from a minimal prompt agent to tool calling, RAG, MCP/Toolbox governance, and a self-hosted agent using the Responses protocol, with practical notes on model routing, deployment, and security.

Lee Stott announces Agents League, a week-long hackathon (part of AI Skills Fest) featuring live “AI coding battles” and project submissions across tracks using GitHub Copilot, Microsoft Foundry, and Copilot Studio, with a $55,000 prize pool and a Microsoft Reactor event series.