Installing a bundle creates a private copy you can edit. The published bundle stays unchanged.
109 bundles
Create evals with unambiguous, programmatically verifiable correct answers
Wrap real or mock APIs into instrumented RL-ready surfaces with deterministic reset, state capture, and action logging
Design and run A/B tests comparing RL-trained agent vs. baseline in production
Diagnose why an RL training run failed and what to change
Determine when prompt engineering, fine-tuning, or RL is the right approach
Estimate total cost (compute, data, engineering time) for an RL project
Read and critically evaluate RL research papers, extract practical implications
Plan RL experiments: baselines, ablations, compute budgets, success criteria
Environments for extraction, classification, and transformation of business documents
Environments for support ticket routing, prioritization, and resolution
Environments mimicking CRM operations (Salesforce, HubSpot)
Environments for building and debugging ETL/ELT pipelines