Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how to build reliable, interpretable AI systems for enterprise workflows in this 26-minute conference talk that addresses the architecture challenges developers face when integrating LLMs into production environments. Discover the design and implementation of an AI orchestration framework that combines LangGraph for multi-agent workflows, Flyte for distributed execution, and AWS Bedrock for LLM inference using Claude 3 to create an AI copilot for enterprise architects. Explore how a domain-specific knowledge graph serves as long-term memory for agents, enabling persistent, structured representations of architectural state, system dependencies, and business context that ground AI recommendations and maintain workflow continuity. Examine the integration of observability practices, including planned OpenTelemetry instrumentation, for tracing and debugging autonomous AI systems in production. Gain an end-to-end blueprint for embedding reasoning capabilities into complex system design and data tasks, moving beyond simple chatbot implementations to sophisticated enterprise-grade AI solutions.
