Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore the evolution from traditional AI-enhanced applications to sophisticated agentic architectures in this comprehensive conference talk. Learn how simple large language model wrappers have transformed into autonomous, stateful systems capable of planning, tool invocation, and collaboration. Discover the journey of building a full-fledged enterprise agentic framework, including the design challenges encountered such as modeling local and long-term memory, representing multi-turn exchanges while preserving context and state, and implementing protocols for interoperability like the Model Context Protocol (MCP) and Agent-to-Agent communication. Examine core concepts and patterns including function calling, memory management, supervision, planning, and workflow orchestration. Understand the architectural trade-offs and practical lessons learned in developing enterprise-grade agentic systems, with insights into observability, security, auditing, and developer experience considerations. Gain practical knowledge from real-world implementation experience, whether you're building your own agent framework or seeking to understand what differentiates agents from traditional AI applications.
