Microsoft Reactor London

Conventional automation executes instructions in order yet modern business scenarios demand reasoning and adaptation. With the new Agent Loop capability in Azure Logic Apps, you can build agentic business processes that adapt to goals, handle retries intelligently and dynamically decide the next step.

In this session, you’ll learn how to combine LLM reasoning with 1,400+ Logic Apps connectors to create workflows that classify, summarize, triage, and resolve tasks in real time. We’ll walk through patterns like nested loops, handoffs, and per-user connections to run processes on behalf of signed-in users.

Expect live demos, practical patterns, and reusable templates you can take back to your own projects to make workflows smarter, adaptive, and scalable without heavy scaffolding.

Join us for an interactive Q&A on Data Engineering in Microsoft Fabric. The Data Engineering team is behind the Spark runtime, notebook and Lakehouse experiences in Fabric—helping you transform, process, and manage data at scale with tools designed to boost both performance and productivity.

We’re here to answer your questions about:

• Apache Spark in Microsoft Fabric: its capabilities, performance, and features
• Best practices for building out your Lakehouse architecture
• How we’re thinking about scaling, performance tuning, and developer experiences

Building AI-powered workflows is only the first step making them secure, reliable, and scalable is where most developers run into challenges. The AI Gateway in Azure API Management provides enterprise-grade tools to expose AI workloads safely and efficiently.

In this session, you’ll learn how to manage token quotas, semantic caching, safety policies, and authentication, ensuring that your AI services perform reliably under load while staying secure. We’ll demo how to wrap AI services in API Management, apply policies for rate limiting, monitoring, and cost control, and optimize AI workload performance in production.

By the end, you’ll have practical patterns and examples for turning AI capabilities into secure, production-ready APIs that your teams can confidently consume.