.NET Rocks! Thinking Agentic AI with Seth Juarez
14 snips
Jul 3, 2025 Seth Juarez, an AI expert from Microsoft, breaks down the intriguing concept of agentic AI, sharing how it can revolutionize development. He discusses the power of tools like MCP and NLWeb for inter-agent collaboration while addressing the challenges of managing these systems. The conversation dives into the technical underpinnings of agentic AI, touching on the limitations and the necessity for proper governance. They also explore the innovative ways prompts can influence AI responses, showcasing the evolving landscape of coding with AI.
AI Snips
Chapters
Transcript
Episode notes
Reasoning Happens in LLMs Only
- AI reasoning is performed exclusively by the LLM; the protocol (MCP) only enables calling functions.
- Reasoning and control happen in prompts and outputs, not in the protocol layer itself.
Language Enables Agent Interaction
- Multi-agent AI systems communicate using natural language prompts as the interface.
- This enables agents to function as tools calling each other dynamically via language.
AI Learned to Subclass Object
- Richard told the AI it needed to subclass an object, even without explicit instructions, it correctly figured out how.
- This showed the AI's ability to learn from partial guidance during coding tasks.