Work

Work & research

I work on how people and agents find knowledge: retrieval, knowledge graphs, 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 current work at Sourcegraph and across SciX.

  • Knowledge graphs

    Entity extraction, linking, and graph-structured representations of knowledge. The method behind this site's own projects explorer.

  • Retrieval

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

  • Agent memory

    How agents store, retrieve, and forget context across turns and sessions. Memory architectures, retrieval over history, and design tradeoffs.

  • Code intelligence

    Understanding codebases at scale: search, navigation, and agents that reason over source. The domain of my work at Sourcegraph.

  • Evaluation & benchmarks

    Measuring whether AI systems work. Benchmarks, evals, and honest comparison of search engines and agents.

  • Scientific search

    Discovery over the scholarly literature. NASA ADS / SciX, citation graphs, and bringing agentic and semantic methods to research workflows.

Selected projects

All projects →
  • Gas City

    An orchestration-builder SDK for multi-agent coding workflows. I'm a maintainer.

  • EnterpriseBench

    A benchmark for evaluating how well coding agents understand and navigate code across large, distributed enterprise codebases.

  • Literature Explorers

    Curated, navigable surveys of recent research, organized into thematic maps rather than linear reading lists. Built on SciX MCP and code-intel sources.

  • Livedocs

    Keep docs in sync with code. Livedocs extracts structural claims from source into per-repo SQLite databases that AI agents query over MCP, no expensive grep-and-read cycles.

  • CodeScaleBench

    A benchmark suite for evaluating how AI coding agents use external context-retrieval tools on realistic developer tasks in large, enterprise-scale codebases.

  • ToM-SWE

    A theory-of-mind agent for Claude Code that learns your coding preferences, interaction style, and project patterns across sessions.

See how it all connects in the graph →

Publications

Research & press →

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