How to Use LangSmith to Achieve a 30% Accuracy Improvement with No Prompt Engineering

In this video we walk through how Dosu uses LangSmith to improve the performance of their application - with NO prompt engineering. Rather, they collected feedback from their users, transformed that into few shot examples, and then fed that back into their application.
This is a relatively simple and general technique that can lead to automatic performance improvements. We've written up a LangSmith cookbook to let anyone get started with continual in-context learning for classification!
LangSmith Cookbook: docs.smith.langchain.com/moni...
Blog: blog.langchain.dev/dosu-langsmith-no-prompt-eng/
Sign up for LangSmith for free: smith.langchain.com/

[@looee___]

Much needed video! Thank you!

[@octopusfinds]

thank you

[@emrecoklar]

Thanks for sharing this. Can you help us with intuition around how this differs from RAG?

[@siyuanrocks]

Imo, this is a RAG system. Langsmith is just playing a role that can help people build up this kind of system rapidly