mcp

AI is evolving beyond individual models toward autonomous agents capable of reasoning, acting and collaborating across tools and systems. This talk looks at how Foundry-based AI platforms, combined with the Model Context Protocol (MCP), help teams move from experimentation to reliable, scalable agentic systems. Focusing on real architectures and deployed use cases, we explore how governance, security and operational control are achieved in practice, how MCP standardizes agent interaction with enterprise systems, and the key trade-offs when building agents that must operate under real-world constraints. Presented at CONVEX 2026 with Manuel Sánchez.