Drew Houston on 400 hours coding with LLMs and Dropbox's AI-first transformation
Knowledge workers face growing information overload with files scattered across multiple apps and screens, making retrieval difficult; earlier classical NLP and tiny pre-GPT LLMs broke down on free-form human language, forcing Drew to abandon multiple automation projects.
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 Q&A
When a user previews a file on Dropbox, an AI integration becomes available for asking questions about it.
Tools used
VS CodeCursorcontinue.devSonnet 3.5LlamaVLLMSGLangXLlamaNext.jsFlaskSQLiteDropbox DashRAGGPT-4
Outcome
Drew built a working personal semantic search engine within days and shipped Dropbox AI (File GPT) with RAG in 2023; relevance and ranking were described as super good even untuned, and Dropbox Dash became a universal search product connecting all apps without file migration.
What failed first
Classical NLP fell apart on natural language, and very small pre-GPT models hallucinated and repeated themselves, causing Drew to write off the approach before the GPT-3/4 era made reliable text understanding possible.