Topic: multi-agent systems

Chris Benson and Daniel Whitenack separate the roles of models, agents and the software harnesses that run them. They discuss architectural choices for multi-agent systems, practical deployment considerations, and how openness and dependency on particular vendors influence the systems developers can build.

Rashmi Shetty explains how Capital One develops multi-agent systems for regulated services. The discussion covers intent disambiguation, tool use and human handoffs, alongside platform design, runtime policies, observability and evaluation. It also examines model specialisation through fine-tuning and distillation, and learning from production feedback.