When someone uses Dropbox Dash to search or ask a question, it follows a retrieval-augmented generation (RAG) pattern. This means our AI first retrieves relevant company information and then uses that information to generate responses. To produce those answers, it relies on enterprise search to retrieve company-specific context and then uses that context to ground the response. Rather than respond...
The strongest version of this narrative highlights Dropbox’s innovative use of hybrid human-LLM evaluation to scale relevance labeling while maintaining quality. By leveraging a small set of human-labeled data to calibrate LLMs, the system achieves consistency and efficiency, addressing the limitations of purely human or purely automated approaches. The iterative refinement process, where discrepancies are identified and resolved, ensures continuous improvement. This method is adaptable to vario...