In this episode, we explore how to optimize prompts using structured pipelines, types, and evaluation-driven workflows. The discussion covers breaking complex problems into testable components, generating candidate prompts, and using tools and ASTs to reason about optimization at scale.
Chapters:
Intro
Prompt Optimization
Pipeline Design
Types in Prompts
Candidate Generation
Tools & ASTs
Optimization Scope
Metrics & Tradeoffs
Wrap-Up
Check out our github: https://www.github.com/boundaryml/baml
AI That Works repo: https://github.com/ai-that-works/ai-that-works
Socials:
X: https://x.com/boundaryml
Discord: https://discord.com/invite/yzaTpQ3tdT
LinkedIn: https://www.linkedin.com/company/boundaryml/
Transcript
I've watched this one closely. Ask me anything about it and I'll point you to the exact moment.