16 posts
Beyond code generation: rethinking engineering productivity in the age of AI agents This blog covers topics presented at the DX Annual 2026 developer productivity conference. For years, engineering productivity has focused on reducing friction inside the software development lif…
Introducing Nova, our internal platform for coding agents Coding agents are becoming an important part of software development. Their most obvious use is helping developers write code faster. But code is only one part of building and operating software. At Dropbox scale, agents…
Improving storage efficiency in Magic Pocket, our immutable blob store Magic Pocket is the core Dropbox storage system—a custom-built, exabyte-scale blob storage system designed for durability, availability, scale, and efficiency. It holds user content, which means it must be sa…
Reducing our monorepo size to improve developer velocity At Dropbox, almost every product change flows through a single place: our server monorepo. A monorepo is a single, shared Git repository that contains many services and libraries used across the company. Instead of splitti…
How we optimized Dash's relevance judge with DSPy Dropbox Dash brings your files, messages, and team’s knowledge together in one place, so you can ask questions and get useful answers that are actually grounded in your company’s context. Under the hood, that experience relies he…
Using LLMs to amplify human labeling and improve Dash search relevance 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 informa…
How low-bit inference enables efficient AI In just the past few years, large machine learning models have made incredible strides. Today’s models are not only remarkably capable but also achieve impressive results across a range of applications, from software engineering and sci…
Insights from our executive roundtable on AI and engineering productivity Improving engineering productivity is crucial to the work we do at Dropbox. The more quickly we can deliver high-quality features to our customers, the more value they can get from our products. This rapid…
Engineering VP Josh Clemm on how we use knowledge graphs, MCP, and DSPy in Dash 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…
Inside the feature store powering real-time AI in Dropbox Dash Dropbox Dash uses AI to understand questions about your files, work chats, and company content, bringing everything together in one place for deeper, more focused work. With tens of thousands of potential work docume…
Building the future: highlights from Dropbox’s 2025 summer intern class This summer, the Emerging Talent team proudly welcomed 43 interns to Dropbox as part of our 2025 Camp Dropbox Intern Program. Representing 27 colleges and universities—including six international institution…
How Dash uses context engineering for smarter AI When we first built Dash, it looked like most enterprise search systems: a traditional RAG pipeline that combined semantic and keyword search across indexed documents. It worked well for retrieving information and generating conci…
With Mobius Labs' Aana models, we're bringing deeper multimodal understanding to Dropbox Dash Teams today create and share more types of content than ever before. Their work might span text, images, audio, and video, and that content is likely scattered across countless apps and…
Half-Quadratic Quantization of large machine learning models Editor's note: We are republishing a blog post from the Mobius team, originally published in 2023, that introduced a now widely used quantization algorithm. We plan to continue this line of work by collaborating with t…
A practical blueprint for evaluating conversational AI at scale LLM applications present a deceptively simple interface: a single text box. But behind that minimalism runs a chain of probabilistic stages, including intent classification, document retrieval, ranking, prompt const…