Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to design and build reliable agentic systems that overcome the inherent unpredictability of non-deterministic decision-making processes in this 18-minute conference talk. Explore how agentic system design differs fundamentally from traditional software development, as these systems must make autonomous decisions that can be difficult to predict or control. Draw insights from interdisciplinary fields including robotics, cybernetics, and biology to develop intuitive approaches for creating systems that achieve greater reliability than their individual stochastic components would suggest. Examine key concepts in agentic system architecture including planning mechanisms, decision-making frameworks, and environmental grounding techniques that enable autonomous systems to operate effectively in real-world scenarios. Discover practical strategies for managing the challenges of building software that must function reliably despite relying on probabilistic processes, with applications spanning multiple industries where autonomous decision-making systems are transforming traditional workflows.
