How we used DSPy to turn AI evaluations into better responses in Dash Chat

· Dropbox · June 25, 2026, 6:22 p.m.
optimization dash llm agents AI Machine Learning Natural Language Processing Chat Applications
Summary
This blog post discusses how the team at Dropbox utilized DSPy to enhance the performance of their large language model (LLM) judges, ultimately improving the responses in their Dash Chat application through an evaluation-driven feedback loop.
Read full post on dropbox.tech →
AUTHOR
Sponsored
Zulip logo Zulip
Organized team chat for people who take work seriously. Topic-based threading keeps conversations focused.
Try Zulip
Become a sponsor →