Copilot Studio Dudecast

The conversation covers the evolution of Copilot Studio, the impact of model improvements on orchestration, and the role and future of child agents and topics. It delves into the early days of Bot Framework Composer, the transition to Power Virtual Agents, and the evolution of the generative orchestrator. It also explores the power and future of child agents and topics in the context of orchestration and agent development. The conversation covers the considerations and limitations of multi-agents, use cases for child and connected agents, context management in multi-agent systems, inputs and outputs in topics and agents, and the excitement and concerns surrounding AI-driven development.TakeawaysEvolution of Copilot StudioImpact of model improvements on orchestrationRole and future of child agents and topics Multi-agents should be used with consideration of trade-offs and limitationsAI-driven development is accelerating workflow and making delivery more efficientChapters00:00 Introduction and Background05:02 Generative AI and Power Virtual Agents10:09 Model Improvements and Impact on Orchestration16:08 Power and Future of Child Agents and Topics28:14 Multi-Agents: Considerations and Limitations35:36 Context Management in Multi-Agent Systems47:38 AI-Driven Development: Excitement and Concerns

In this episode, I talk with Bas Brekelmans, CTO of Copilot Studio. The conversation covers the evolution of conversational AI models, challenges in managing and deploying the latest models, the impact of model evolution on performance and security, and the shift in building agents from specific workflows to evaluating expected outcomes. The discussion also delves into the history and evolution of conversational AI, early models and innovation, challenges of model management, model selection and orchestration, security and guardrails in model orchestration, performance and latency in model orchestration, and the evolution of building agents. The conversation delves into the impact of AI models on engineering discipline, the transition from traditional development to model training, and the evolution of skill sets in natural language understanding. It also explores the role of language proficiency in AI development and the evolution of AI systems and models.TakeawaysEvolution of conversational AI modelsChallenges in managing and deploying the latest modelsImpact of model evolution on performance and securityShift in building agents from specific workflows to evaluating expected outcomes Nudging AI modelsTransition from traditional development to model trainingChapters00:00 Evolution of Building Agents30:06 Automating Reordering and Over-Engineering36:12 Evolution of Engineering Discipline41:33 Transition to Managerial Role in AI Development48:10 Evolution of AI Systems and Models

In this episode of the Copilot Studio Dudecast, I talk with Jeff Derstadt. Jeff is a Partner Engineering Director in Copilot Studio's Engineering team. We discuss the evolution of Copilot Studio from the beginning, the importance of instructions and descriptions and many other great topics in this episode.

In this episode of the Copilot Studio Dudecast, I talk with Andy Matkin. Andy was the lead architect of Nuance Mix and is a senior technical engineer in Copilot Studio's Engineering team. We discuss MCP and many other great topics in this episode.