Prompt Optimization w/ DSPy
As vibe checks become generally good no matter which models you pick up, it becomes more important than ever to be able to optimize your prompts.
This is the natural next step.
In our revisit of DSPy, we’re going to cover the state of prompt optimization and what you need to know to “optimize over your agent’s harness.”
Of course, we’ll define both Prompt Optimization and introduce why DSPy is the best-practice tool today.
Previously, in 2024, we covered DSPy in three steps:
This time, we’ll cover the evolution of the DSPy ecosystem since last year, including it’s usage in:
evaluation-driven systems
agent optimization loops
Of course, we’ll cover in detail the big release of the year from the DSPy team was the GEPA (Genetic-Pareto) optimizer, which “thoroughly incorporates natural language reflection to learn high-level rules from trial and error.”
Additionally, specifically, we’ll dive into the “three stages of building AI systems in DSPy,” which include:
DSPy Programming
DSPy Evaluation
DSPy Optimization
And of course, we’ll cover where DSPy should fit into your prompt optimization toolkit as an AI Engineer after we build, ship, and share an optimized agent or two!
🤓 Who should attend
Engineers, data scientists & ML enthusiasts, researchers, and anyone who loves optimizing.
AI Engineers and leaders looking to stay out on the edge of prompt optimization
Speaker Bios
Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for The AI Engineering Bootcamp. Since 2021, he has built and led industry-leading Machine Learning education programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher. He loves trail running and is based in Columbus, Ohio.
Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for The AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator whose motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.
Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.