Dropbox

How we optimized Dash's relevance judge with DSPy

Manual prompt engineering for Dropbox Dash's relevance judge was unreliable, hard to measure, and costly—making it difficult to systematically improve task performance in production.

ml-systems search
3 min
Dropbox

Using LLMs to amplify human labeling and improve Dash search relevance

Dash's search ranking models required large volumes of high-quality labeled relevance data to train effectively, but human labeling alone was too slow and expensive to scale to the needed coverage.

search ml-systems
3 min
Dropbox

How low-bit inference enables efficient AI

Running AI inference for products like Dropbox Dash at scale is expensive and resource-intensive, requiring efficient use of compute and memory to make the product accessible to a broad user base.

ml-systems storage-systems
3 min
Dropbox

Insights from our executive roundtable on AI and engineering productivity

Engineering organizations face open questions about how to effectively integrate AI coding tools (like Claude Code and Cursor) into developer workflows and where these tools can have the most measurable impact on productivity.

ml-systems microservices
4 min
Dropbox

Engineering VP Josh Clemm on how we use knowledge graphs, MCP, and DSPy in Dash

Enterprise search and AI assistant products like Dropbox Dash need to connect disparate data sources and optimize AI-driven retrieval, but naively querying across siloed data with LLMs leads to poor relevance and brittle prompt engineering.

search ml-systems
3 min
Dropbox

Inside the feature store powering real-time AI in Dropbox Dash

Dropbox Dash needs to rank and retrieve relevant context across a user's work in real time, requiring low-latency access to precomputed and real-time features for AI-driven search and recommendation models.

ml-systems real-time-systems
3 min
Dropbox

How Dash uses context engineering for smarter AI

Dropbox Dash's AI agent struggled with effectiveness when naively providing all available context to the model, leading to degraded performance as irrelevant information diluted the signal needed for accurate, agentic AI responses.

ml-systems search
3 min
Dropbox

Half-Quadratic Quantization of large machine learning models

Large machine learning models require significant memory and compute resources, making deployment and inference expensive and slow, especially in resource-constrained environments.

ml-systems storage-systems
3 min
Dropbox

With Mobius Labs' Aana models, we're bringing deeper multimodal understanding to Dropbox Dash

Dropbox Dash needed deeper understanding of multimodal content (photos and videos) across user files, but processing diverse media types at Dropbox's scale posed efficiency and architectural challenges.

ml-systems search
3 min