• I was recently a guest speaker in Jason Liu’s online course on RAG offered by the education platform Maven. • I did some mini deep-dives into what we’ve been doing at Dropbox with knowledge graphs; how we’re thinking about indexes, MCP, and tool calling in general; some of the work we do with LLM as a judge; and how we use prompt optimizers like DSPy. • This is an edited and condensed version of my talk. • Visit Maven to watch the full video and hear my Q&A with Jason and his students. • - Josh Clemm, vice president of engineering for Dropbox Dash ~ ~ ~ I don’t know about you, but I probably have about 50 tabs open right now-and at least another 50 accounts for other SaaS apps. • It’s completely overwhelming.
Article Summaries:
- Dropbox’s engineering team, led by VP Josh Clemm, announced that its new product, Dropbox Dash, leverages knowledge graphs, multi‑component pipelines (MCP), and the prompt‑optimization framework DSPy to unify work content across disparate SaaS apps. Dash connects to third‑party services via custom crawlers, normalizes files into a common format, extracts metadata and embeddings, and applies multimodal models for images, PDFs, audio, and video. The system then constructs a graph linking documents, meetings, people, and notes, feeding the data into secure lexical indexes (BM25) and embedding stores. Clemm highlighted the platform’s focus on secure, cross‑app context to enable advanced search and agentic queries for enterprise users.
Sources: