Research
We do applied research. That means we start with real problems, build things, run experiments, and publish what we learn. No hand-waving about what AI might do someday. We care about what actually works right now.
Publications
Code Retrieval in Coding Agents
Why do coding agents work well on small projects but struggle with large codebases? We studied how different coding agents find and use code context. Turns out the retrieval problem is where most agents fall apart.
Experiments
Smaller projects and benchmarks from our research. Completed explorations, not ongoing work.
Code Context
Semantic code search with APIs similar to ripgrep. An experiment in figuring out the best way to provide code context to coding agents.
EmojiBench
A benchmark designed to detect AI-generated code by measuring emoji usage patterns.
Sync Engine
A sync engine for building offline-first applications with automatic conflict resolution and optimistic updates.
Code Retrieval Eval
Evaluation framework for measuring how well coding agents retrieve relevant code from large codebases. Built for our code retrieval research.
Blog
Longer-form thinking and observations from our work.
Why Senior Engineers Get More Out of AI Than Junior Developers
A counterintuitive pattern: senior engineers consistently extract more value from AI coding tools than juniors. It's not about prompt tricks. It's about judgment.