Work

Work & research

I work on how people and agents find knowledge: retrieval, agents, and the evaluation of the systems we build.

Focus areas

AI agents

Systems that plan, call tools, and act over multiple steps to accomplish a goal. The throughline of my work, from software factories to scientific search.
Retrieval

Finding the right information at the right time. Embeddings, ranking, hybrid search, and retrieval-augmented systems over scientific and code corpora.
Code intelligence

Understanding codebases at scale: search, navigation, and agents that reason over source.
Evaluation & benchmarks

Measuring whether AI systems work. Evals and benchmarks of agents and agentic retrieval.

SciX Agent
An agentic research assistant over the NASA SciX / ADS corpus, bridging AI agents with scholarly search infrastructure.
Gas City
An orchestration-builder SDK for multi-agent coding workflows. I'm a maintainer.
CodeScaleBench
A benchmark suite for evaluating how AI coding agents use external context-retrieval tools on realistic developer tasks in large, enterprise-scale codebases.
EnterpriseBench
A benchmark for evaluating how well coding agents understand and navigate code across large, distributed enterprise codebases.
CodeProbe
Benchmarks AI coding agents against your own codebase by mining evaluation tasks from its git history, so the suite can't be contaminated by training data.
mem
Build and benchmark agentic memory using a multi-agent orchestrator's own work traces as the evaluation corpus, where every unit of work carries a real lifecycle outcome and a full trace.

Peer-reviewed work and preprints in planetary science and information science.