[Cologne] AI Dev Night with Microsoft and Elastic


Oct 22 2026, 06:00 PM CEST. Add to calendar: Google | Outlook
  • KölnBusiness, Börsenpl. 1, 50667 Köln, Germany Elastic
  • 1 RSVPs
Description

Join us for an evening of deep technical dives and networking! This developer night explores the critical path of taking AI agents from concept to production on Azure. We will go beyond basic AI demos to tackle the real-world challenges of identity, strict data authorization, and observability using the combined power of Microsoft and Elastic.

Who Should Attend:
Software Developers, AI/ML Engineers, Cloud Architects, and Security Professionals interested in building secure, production-ready Generative AI applications on Azure.

Agenda:
* 6:00pm~6:30pm: Checkin, Food and Networking
* 6:30pm~8:30pm: Tech talks and Q&A
* 8:30pm: Open discussion and Mixer

Tech Talk: Ship Agents, Pass Risk Review: Microsoft Foundry + Elastic on Azure
Speaker: Mike Richter, Principal Partner Solution Architect at Microsoft
Abstract: In this session, I’ll share how I built ELK Burgers, an agent-governance demo using Microsoft Foundry Hosted Agents and Elastic on Azure, and the lessons learned moving toward production readiness. Using synthetic contracts and operating manuals for a fictional restaurant chain, we’ll ask the same question of an intentionally over-permissioned assistant and four agents scoped for different jobs.

Tech Talk: RAG is Broken: How Elastic & Azure Fix Context, Latency, and Token Bills
Speaker: Francois Protopapa, Principal Solutions Architect at Elastic
Abstract: Scaling Generative AI from a promising PoC to enterprise-grade production is where many digital initiatives hit a wall. Unpredictable Azure OpenAI token costs, creeping response latencies, and inaccurate context delivery actively threaten project ROI and user adoption. Relying on pure vector search is no longer enough to support business-critical operations.
In this session, we will explore how advanced Context Engineering and Elastic’s hybrid retrieval optimize context accuracy—drastically cutting prompt size, response latency, and cloud API overhead. Furthermore, learn how Elastic LLM Observability (built on OpenTelemetry) delivers total operational visibility, allowing leaders to track token spend, monitor accuracy, and govern AI investments on Azure in real time.

Venue:
KölnBusiness, Börsenpl. 1, 50667 Köln, Germany

Local and Global AI Community on Discord
Join us on discord for local and global AI tech community:
- Events chat: chat and connect with speakers and global and local attendees;
- Learning AI: events, learning materials, study groups;
- Startups: innovation, projects collaborations, founders/co-founders;
- Jobs and Careers: job openings, post resumes, hiring managers



Contact Organizer