Agentic Prompt Optimization

Learn a practical method to optimize LLM prompts iteratively using an LLM as the optimizer, improving system prompts and discovering vulnerabilities.

Overview

What if you could optimize your prompts the way you optimize model weights — with a loss function, an optimizer, and an iterative loop?
This talk presents a practical methodology for agentic prompt optimization: using an LLM as an optimizer to iteratively improve system prompts against a test suite, treating prompt text as a tunable parameter rather than a static artifact.

Tech stack