The new experience allows users to ask Dropbox to organize files and answer questions about content, with all results remaining within the platform.
The system uses isolated VMs and conversation-specific undo to let users direct file tasks while retaining control over permissions and changes.
Reclaim uses a custom agent loop and 'Preview Mode' to let users review AI-suggested calendar changes before they affect other attendees.
Dropbox has recorded a 70% AI-generated code ratio and achieved top 5% industry performance in PR throughput.
Dropbox has released modernized API documentation that supports MCP server integration and an AI assistant.
Dropbox has developed an internal audit tool that automatically verifies whether user privacy settings are correctly applied across more than 200 web pages.
Dropbox is pursuing a strategy to optimize existing infrastructure from a systems perspective and maximize efficiency to address the surge in AI demand.
This describes how Dropbox optimized and evolved Riviera, its content processing platform developed over 10 years, for AI.
Dropbox leveraged DSPy to refine its LLM-based evaluation model, thereby improving both the response quality and efficiency of the Dash Chat agent.
Dropbox combined MCP and Dash to build a system that automatically verifies whether security design requirements are reflected in actual code implementation.
Dropbox is redefining productivity across the entire engineering workflow, beyond code generation, through its AI agent platform Nova.
Dropbox built an internal coding agent platform called **Nova**, tailored to its large monorepo and CI.
Dropbox introduced L1·L2·L3 compaction to lower Magic Pocket's storage overhead once again.
Dropbox reduced its monorepo from 87GB to 20GB by adjusting Git's packing method.
DSPy made Dropbox Dash's relevance judge cheaper and more accurate.
After calibrating an LLM with a small amount of human labels, it automatically generates relevance labels at scale.
Low-bit inference reduces memory and computation to make AI models faster and cheaper.
Dropbox scaled AI adoption company-wide, lifting both PR throughput and developer sentiment.
Dropbox Dash reduces tokens and latency through index, knowledge graph, and MCP optimization.
Dropbox built a feature store for sub-100ms ranking using Feast, Go, and Dynovault.
43 Dropbox summer 2025 interns spent 12 weeks improving Dash and core infrastructure.
Dash improved agent accuracy by reducing the number of tools and keeping only relevant context.
AI Briefing