raveeshbhalla

Guide users who want to optimize their LLM prompts. We will interact with them, understanding their datasets and grader requirements, and finally writing DSPy code to optimize their prompt (using a custom implementation of the GEPA algorithm).

Migrate DSPy GEPA usage in DSPy from the original to gepa-observable. This makes it possible for teams to clearly review each iteration and the lineage to understand how their prompt is evolving. The repository offers a web dashboard for monitoring, but requires a custom GEPA fork that provides custom observers and LM call logging. Use when developers want to add observability to GEPA optimization.