← back

Everything Is a Rollout — Alex Shaw + Ryan Marten, Terminal-Bench, Harbor, Laude Institute

1.6K views · Jul 24, 2026 · 21:11 min · Watch on YouTube ↗
Takeaway

Evaluate and improve agents through repeatable environment rollouts with explicit verification and preserved trajectories.

Summary

  • Harbor treats agent development as empirical machine learning: environments serve as data, prompts and tools act like tunable parameters, and reward hacking resembles overfitting.
  • An evaluation environment combines a task instruction, a sandbox where the agent acts, and a verifier that checks the resulting state.
  • Harbor packages environments as interoperable directories and supports agents running either inside or outside the sandbox.
  • A rollout starts the environment, executes the agent until a stopping condition, records its trajectory, runs verification, and tears down the sandbox.
harboragent-evaluationrl-environments
Original description
Alex Shaw and Ryan Marten present a rollout-centered view of evaluating and improving AI agents. Drawing on their work on Harbor, Terminal-Bench, and OpenThoughts-Agent, they connect sandboxed environments, agent evaluations, and optimization workflows into a practical framework for generating and learning from rollouts.

Speakers:

Alex Shaw — Member of Technical Staff, Laude Institute
Alex is the creator of Harbor, a framework for evaluating and optimizing agents and language models in sandboxed environments.
  / alexgshaw  

Ryan Marten — Member of Technical Staff, Laude Institute
Ryan builds Harbor and works on research-to-production efforts including Terminal-Bench and OpenThoughts-Agent.
  / ryan-marten  

Harbor: https://www.harborframework.com/
GitHub: https://github.com/harbor-framework/h...