Absract
Agents can utilize tools to access real time data and to invoke business logic. Agentic applications can even generate execution plans how multiple agents should be orchestrated for specific tasks. While the capabilities are evolving quickly, agents don't always work reliably. Developers and AI Engineers need to understand how these systems work to improve them. Because of the level of complexity, observability for agents is even more important than for Large Language Models only. In this session you'll learn why observability and transparency are key topics for agents and how the open-source agent framework 'Bee' helps developers to understand agentic flows.
Topics To Be Covered
How agents utilize real-time data
Orchestrating multiple AI agents
The importance of observability in AI
Open-source agent framework
Who Is This For?
AI Engineers & Developers
Conversational AI & NLP Experts
Machine Learning & Data Science Teams
Tech Leads & Software Architects
Meet Your Speaker
AI Engineer and Developer, IBM
Niklas Heidloff is the CTO Partner Co-Creations EMEA at IBM, where he leads strategic partnerships in building and deploying enterprise AI solutions. With over 15 years at IBM in senior technical roles, he has built extensive expertise in cloud platforms and open-source development, essential components for implementing AI at scale.
A builder and AI engineer at heart, Niklas has served as Developer Advocate for IBM Cloud and consistently contributes to advancing enterprise AI deployment through his technical blog and open-source initiatives. His work focuses on implementing robust AI systems that create tangible business value, sharing practical insights on successfully deploying AI capabilities in enterprise environments.
ADDITIONAL INFORMATION
Time & Place
April 1, 2025
14:00 - 15:00
The Ritz-Carlton Berlin
Salon Tiergarten
Classroom Seating
Notes
Agenda for this session
5 min introduction
25 min presentation
15 min Q&A
.png)