Dropbox Tech·unknown·10 min read·
Ilya Yakovlev,Andrew Cheung,Binoy Dash,Simran Jumani,Dmitriy Meyerzon
60
How we used DSPy to turn AI evaluations into better responses in Dash chat
We used DSPy to improve LLM judges and optimize our chat experience, creating an evaluation-driven feedback loop that produced better outputs.
Score breakdown
- Technical depth52
- Practical value100
- Originality60
- Writing quality94
- Source reputation85
- Recency2
- External engagement0
- On-site engagement0
More like this
Yelp Engineering30
Beyond the Menu Tree: How Yelp Built a Smarter Customer Success Chatbot with AI
Lina Lee, Machine Learning Engineer; Nelson Lee, Engineering Manager
·unknown·1 min read
Airbnb Engineering53
From weeks to a day: how we made LLM evaluation fast enough to iterate on
Baharak Saberidokht·unknown·10 min read
Etsy — Code as Craft51
Context engineering case studies: Etsy-specific question answering
Jerome Bellegarda·unknown·12 min read
The Cloudflare Blog49
From ranking to recommended: get your site ready to thrive in the age of AI agents
Matthew Conroy·unknown·7 min read
Engradar shows a summary and links to the original article. The full article is hosted on dropbox.tech.