Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore the architecture and optimization of advanced AI agents in this 32-minute conference talk from the Linux Foundation's Open Source Summit. Learn how to build modular iterative reasoning patterns for complex tasks on private enterprise data, with a focus on Deep Research agents. Discover the implementation of LLM-as-a-judge evaluation methods when gold standard benchmarking datasets are unavailable, and understand how evaluation signals can drive end-to-end optimization of modular non-differentiable systems to enhance performance. Gain insights into the practical challenges and solutions for deploying sophisticated AI agents in enterprise environments, covering both the technical architecture and evaluation methodologies essential for building robust AI systems.
