Dropbox brings AI-powered summarization and Q&A to web file previews using Riviera and LLMs
Knowledge workers suffer from information overload and need to understand large documents, videos, and other files without reading them in full or remembering exactly how content was worded or where it was located within a file.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · File preview triggers AI request
A user previews a file on the Dropbox web interface, triggering AI-powered summarization or Q&A.
Tools used
RivieraLLMsk-means clustering
Outcome
After optimization, cost-per-summary dropped by 93% and cost-per-query dropped by 64%. P75 latency for summaries decreased from 115 seconds to 4 seconds, and p75 latency for queries decreased from 25 seconds to 5 seconds, making the feature more affordable and more responsive for users.
What failed first
An earlier summary-of-summaries (map-reduce) approach repeated information across individual summaries, caused significant loss of overall file content, and compounded hallucination risk with each additional LLM call. The initial version also did not cache embeddings, resulting in redundant LLM calls for the same document.