Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how to replace manual prompt crafting with a test-driven, automated approach in this 14-minute conference talk from the AI Engineer World's Fair. Discover why traditional hand-tuning of prompts doesn't scale and explore modern techniques for defining output evaluators, writing minimal prompts, and enabling agents to iterate toward optimal performance without manual intervention. Understand the fundamental shift from manual prompt engineering to automated systems that can self-optimize. The session demonstrates practical methods for implementing test-driven prompt development and shows how to build systems that improve themselves over time. Gain insights from Nir Gazit, CEO of Traceloop and former chief architect at Fiverr and tech lead at Google, who argues that manual prompt tweaking is an outdated practice that should be replaced with systematic, automated approaches to achieve better results at scale.
