How our universal content processing platform Riviera evolved for AI and beyond
- Source
- dropbox.tech
- Author
- Ilya Yakovlev,Andrew Cheung,Binoy Dash
- Date

Context
Dropbox's Riviera platform prepares files for several products by reusing small content-conversion steps. A presentation can become a PDF and then page images; those same transformations can serve other workflows. A central coordinator validates requests, dispatches work and caches results so products can reuse completed transformations. Dropbox's account describes how a preview service became shared infrastructure.
Dash uses that infrastructure to extract document text, recognize scanned pages and prepare metadata before search and AI systems use the content. This gives the AI product an existing route from varied file formats to usable . Improvements to a shared transformation can then benefit other products using the same step.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
- MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
articleHow AI-assisted development helped us build the new Dropbox experienceDaniel Reiter Horn,Rich Chan,Pravi Garg,Sourabh Yerfule,Gennadiy Civil
articleWhat Dropbox has learned from deploying AI at company scaleDropbox Team
articleHow Dropbox uses MCP and Dash to close the design-to-code security gapIlya Yakovlev,Andrew Cheung,Binoy Dash,Simran Jumani,Dmitriy Meyerzon,Mark Breitenbach,Ishan Mishra
Checking sign-in…
Loading comments…