• Harbor Framework → Present github.com

    Core maintainer of Harbor — an open-source evaluation harness for running and grading agentic terminal tasks at scale.

    Agentic SystemsAgent EvaluationOpen Source
  • Challenges of Agent Design → ne-agents-day.github.io

    An oral paper at the NE Agent Day workshop — profiling the efficiency and design challenges of agentic systems, with Prof. Gupta's group at Cornell.

    Agentic SystemsEfficiencyProfilingResearch