Artificial Intelligence1 min read

How two engineer side projects became the agent taking action inside Dropbox

By · Published by Everything Blog

In short

The initiative stems from internal experiments where engineers used coding agents to file expense reports and generate 3D models. Daniel Reiter Horn created a sandboxed computing workspace via rclone, while Rich Chan built an interface linked to folder pickers and live previews. Merging these designs enabled a unified setup pre-equipped with software for spreadsheet editing, audio transcription, video editing, and diagramming. Users can track the agent's real-time actions, approve permissions, and undo any unwanted changes using standard rollback features.

Key points

  • Dropbox users can now deploy autonomous agents to directly organize, rename, and prepare…: Dropbox users can now deploy autonomous agents to directly organize, rename, and prepare files without downloading them locally.
  • Safety controls ensure that every action taken by the AI respects permissions, offers liv…: Safety controls ensure that every action taken by the AI respects permissions, offers live progress tracking, and can be undone via version history.
  • The product originated from two employee side projects that adapted coding agents for eve…: The product originated from two employee side projects that adapted coding agents for everyday tasks like expense reports and 3D modeling.

Sources checked by our analysis pipeline: 1

AI can help people turn an idea into a first draft, but getting to something usable depends on more than a prompt. It needs the files and context behind the request, software to carry out the work, and a way for people to review and refine the result. With the new Dropbox experience, we’re bringing those pieces together where people already keep their work, so they can ask questions about their content and request tasks such as organizing folders, renaming files, and preparing materials to share. Letting an agent change those files meant giving it a controlled place to work, enforcing permissions, and recording its changes so people could review and undo them.

The agent behind those tasks started as two experiments, each approaching the same problem from a different angle. Daniel Reiter Horn and Rich Chan, engineers at Dropbox, were using coding agents for tasks beyond writing software, including designing 3D-printed models and filing expense reports. Both encountered the same challenge: giving an agent access to their Dropbox files while retaining control over what it changed and a way…

Artificial Intelligence