Prompt Like a Data Scientist: Auto Prompt Optimization and Testing with DSPy

Applying machine learning methodology to prompt building

LLMs are grounded in data science, but our approach to prompt engineering might strike us as unscientific:

1. Manual prompt engineering which does not generalize well: LLMs are highly sensitive to how they are prompted for each task, so we need to handcraft long strings of instructions and demonstrations. This requires not only time-consuming prompt writing process, but the given string prompt might not generalize to different pipelines or …

ai data science deep-dives llm openai