Reproducible eval sandbox for testing Computer Use / browser agents on monitor competitor pricing in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on reconcile invoices in QuickBooks in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on triage tickets in Zendesk in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on extract leads from Apollo.io in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on schedule posts in Buffer in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on pull metrics from Mixpanel in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on fill job applications on company portals in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on download reports from Stripe dashboard in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on apply to jobs on LinkedIn in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on scrape product listings on Amazon in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on pull analytics from GA4 dashboard in developer tooling context. Fixture sites, gold trajectories, and regression gates.
Reproducible eval sandbox for testing Computer Use / browser agents on fill expense reports in Concur in developer tooling context. Fixture sites, gold trajectories, and regression gates.