Microsoft Reactor London

Join us for an exciting deep dive into the world of autonomous AI agents with a focus on Semantic Kernel and the experimental integration of AutoGen. In this session, we'll explore how these tools can be harnessed to build intelligent agents capable of independently executing complex tasks or collaborating seamlessly with humans in real time.

You’ll gain insight into how Semantic Kernel enables developers to orchestrate AI capabilities through a powerful, open-source SDK that integrates natural language processing, memory, planning, and connectors to external systems. We'll also discuss the experimental use of AutoGen, a framework designed to facilitate the creation of multi-agent systems, allowing LLM-powered agents to communicate, delegate, and solve problems collaboratively.

Whether you're a seasoned developer, an AI enthusiast, or simply curious about the next frontier of AI innovation, this talk will provide you with practical examples, demo walkthroughs, and the foundational knowledge to start building your own autonomous AI workflows.

Key Takeaways:

• Understand the architecture and use cases of Semantic Kernel
• Learn how AutoGen enables multi-agent collaboration
• See real-world demos of agents completing complex tasks
• Leave with actionable resources to start experimenting

Suggested Microsoft learn modules:

Attackers are now taking advantage of AI to employ TTPs that cover more attack surface faster than ever before; consequently, web app penetration testing, red teaming, and blue team reaction time has moved from the speed of a go-kart track to the speed of a F1 race, in order to cover the same amount of ground as attackers.

Please join Achilleus to hear first-hand from one of the best offensive tester/red teamers in the world, as to what we can expect from attackers in 2025 as well as how to level the playing field and give an edge to the developing and security teams.

The rise of multi-agent AI applications is transforming how we build intelligent systems - but how do you architect them for real-world scalability and performance? In this session, we’ll take a deep dive into a production-grade multi-agent application built with LangGraph for agent orchestration, FastAPI for an API layer, and Azure Cosmos DB as the backbone for state management, vector storage, and transactional data.

Through a detailed code walkthrough, you’ll see how to design and implement an agent-driven workflow that seamlessly integrates retrieval-augmented generation (RAG), memory persistence, and dynamic state transitions. We’ll cover:

• Agent collaboration with LangGraph for structured reasoning
• Real-time chat history storage using Azure Cosmos DB - the same database that powers the chat history in ChatGPT, the fastest-growing AI agent application in history
• Vector search for knowledge retrieval with Cosmos DB's native embeddings support
• FastAPI’s async capabilities to keep interactions responsive and scalable

By the end of this session, you’ll have a clear blueprint for building and deploying your own scalable, cloud-native multi-agent applications that harness the power of modern AI and cloud infrastructure. Whether you're an AI engineer, cloud architect, or Python developer, this talk will equip you with practical insights and battle-tested patterns to build the next generation of AI-powered applications