Global Agentic Nights - London
Global Agentic Nights are vibrant, community-driven evenings by Global AI Community designed to bring together AI enthusiasts, professionals, and curious minds from around the world.
5:30-6:00pm: Welcome and Networking
6:05 PM – 6:20 PM - Trevor Horwitz – Managing Director, Cyber & Data Resilience @ Kroll
Session - Enterprise Risk of Agentic AI
6:30 PM – 7:00 PM - Dieter Gobeyn - Enterprise Integration Architect & Azure Cloud Solutions Architect
Session - AI Meets Integration: Building Smart Agents in Azure Logic Apps
Discover how Azure Logic Apps is evolving with AI. This session introduces the new Agent Loop feature, blending traditional workflows with intelligent agents. Learn when to use agents vs workflows, how to integrate prompts, tools, and connectors, and see a live demo of building an AI-powered agent. Perfect for developers and architects ready to bring intelligence into their automation.
7:00 - 7:30pm Break / Networking
7:30 PM – 8:00 PM - Matteo Emili - Director of Software Engineering @ Avanade UK & Ireland
Session - Going from vibe coding to Agentic Engineering, a step-by-step guide
Software development is evolving from “vibe coding”, where intuition and spontaneous creativity drive progress, to "agentic engineering", a more regulated and governed approach. In this new paradigm, AI agents collaborate with developers not only to unlock creativity, but also to ensure adherence to best practices and organizational guidelines. By harnessing agentic workflows, teams can capture the imaginative potential of AI while embedding robust standards, governance, and process discipline into everyday coding. This session explores how agentic engineering blends innovation with accountability to reshape the future of software development.
8:00 PM – 8:30 PM - Richmond Alake | Staff Developer Advocate @ MongoDB
Session- Memory Engineering aka Context Engineering
Large Language Models (LLMs) are powerful, but their limitations become clear in multi-turn interactions: they lose track of context, repeat mistakes, and forget what matters. Lately, developers have relied on context engineering—clever prompt design, retrieval pipelines, and compression—to work around these constraints. But context alone is ephemeral. To build agents that are reliable, believable, and capable, we need to move beyond context and into memory engineering.
This talk introduces memory engineering as the natural progression of context engineering, exploring how to design systems where data is intentionally transformed into persistent, structured memory that agents can learn from, recall, and adapt with over time. We’ll walk through the data→memory pipeline, types of agent memory (short-term, long-term, shared), and practical strategies like reflection, consolidation, and managed forgetting
End 8:30PM approx
#Microsoft #AzureAI #MicrosoftCommunity #Azure