Dropbox Tech Blog
We used DSPy to improve LLM judges and optimize our chat experience, creating an evaluation-driven feedback loop that produced better outputs.
Dropbox Tech Blog •
Dropbox Tech Blog
Using an agentic AI system to surface threat models during code review and spot gaps between security requirements and implementation.
Dropbox Tech Blog •
Dropbox Tech Blog
How Dropbox is moving from AI tools that assist engineers to agentic systems that can execute scoped tasks, and how we’re building platforms to support those workflows.
Dropbox Tech Blog •
Dropbox Tech Blog
Nova lets engineers run multiple coding sessions in parallel and lets internal systems use AI agents as part of automated workflows.
Dropbox Tech Blog •
Dropbox Tech Blog
By turning compaction into a layered, adaptive pipeline and strengthening our monitoring and controls, we made Magic Pocket more resilient to workload changes.
Dropbox Tech Blog •
Dropbox Tech Blog
Monorepos will continue to grow as products evolve, but growth doesn’t have to mean friction.
Dropbox Tech Blog •
Dropbox Tech Blog
We used DSPy to turn prompt engineering for our relevance judge into a measurable, automated optimization loop, improving task performance, cost, and how reliably it works in production.
Dropbox Tech Blog •
Dropbox Tech Blog
How we train Dash's search ranking models with a mix of human and LLM-assisted labeling.
Dropbox Tech Blog •
Dropbox Tech Blog
Making products like Dropbox Dash accessible to individuals and businesses means tackling new challenges around efficiency and resource use.
Dropbox Tech Blog •
Dropbox Tech Blog
From Claude Code to Cursor, we're big adopters of AI coding tools at Dropbox. The early results have been promising, but there are still a lot of open questions about how to work with these tools most effectively and where they can have the most impact. To push this conversation forward, we hosted an executive roundtable at our San Francisco studio. Here's how it went.
Dropbox Tech Blog •