Building robust agent systems requires far more than simply chaining prompts together linearly. While many projects start with simple chains, production use calls for architectures that can reliably handle errors, process asynchronous events, and manage complex state.
In this session, we take a concise look at modern orchestration approaches for AI agents, analyze their strengths and weaknesses, and show which architecture type is best suited to which challenges—from simple pipelines and graph structures to decoupled multi-agent systems. Attendees will gain an overview to help them select the right orchestration pattern for their specific requirements and build systems that scale as complexity grows.
Speakers:
Martin Brandl (CTO, white duck)
André Ratzenberger (Senior Software & AI Architect, white duck)
👉🏼 Tickets can be purchased via this link.
