Media Summary: In this video, we talk about Stanford NLP's How to code an automatic prompt optimizer. How the most advanced prompt optimization tool, Large Language Models (LLMs) excel at understanding messy, real-world data, but integrating them into production systems ...
Developing Dspy Metrics Debugging Dspy - Detailed Analysis & Overview
In this video, we talk about Stanford NLP's How to code an automatic prompt optimizer. How the most advanced prompt optimization tool, Large Language Models (LLMs) excel at understanding messy, real-world data, but integrating them into production systems ... Applications developed for the enterprise need to be rigorous, testable, and robust. The same is true for applications that use AI, ... This is a single lecture from a course. If you you like the material and want more context (e.g., the lectures that came before), check ... Prompt engineering doesn't scale—especially when models change, prompts drift, and your “logic” lives inside a giant string.
[2026 - Day 2 - Workshop] Sustainable prompt engineering is a challenge. Every time we change a model, update the distribution ... Can algorithmically optimizing prompts outperform prompt engineering? Resources: As model performance converges, prompt optimization is the new competitive edge. In this session, we revisit ai.bythebay.io Nov 2025, Oakland, full-stack AI conference
![Using DSPy for Prompt Optimization in Python: Example of Calibrating Quiz Bowl Questions [Lecture]](https://i.ytimg.com/vi/sG3Tz0-Vw58/mqdefault.jpg)
