Microsoft Reactor London

Now that we're more than halfway through our Python + AI series, we're covering a crucial topic: how to use AI safely, and how to evaluate the quality of AI outputs.

There are multiple mitigation layers when working with LLMs: the model itself, a safety system on top, the prompting and context, and the application user experience. Our focus will be on Azure tools that make it easier to put safe AI systems into production.

We'll show how to configure the Azure AI Content Safety system when working with Azure AI models, and how to handle those errors in Python code. Then we'll use the Azure AI Evaluation SDK to evaluate the safety and quality of the output from our LLM.

Pre-requisites:
If you'd like to follow along with the live examples, make sure you've got a GitHub account.

For the penultimate session of our Python + AI series, we're building AI agents! We'll use many of the most popular Python AI agent frameworks: Langgraph, Semantic Kernel, Autogen, Pydantic AI, and more.

Our agents will start simple and then ramp up in complexity, demonstrating different architectures like hand-offs, round-robin, supervisor, graphs, and ReAct.

Pre-requisites:
If you'd like to follow along with the live examples, make sure you've got a GitHub account.

Today’s DevSecOps pipelines excel at finding issues, but not at knowing which ones truly matter. Traditional testing tools stop at detection, while real security validation often happens late, manually, and out of band.

In this session, we’ll explore what it means to bring offensive security intelligence into the developer workflow, unifying detection, validation, and remediation in a continuous loop. Using XBOW as an example, we’ll discuss how AI-driven reasoning can help teams move from theoretical findings to proof-backed, fix-verified security that keeps pace with modern development.

You'll learn:

• Why DevSecOps needs real-world validation (not just scanning) to close the loop
• How shifting offensive testing left changes prioritization, collaboration, and velocity
• How AI is reshaping the path from vulnerability discovery to verified remediation