Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Rust agentai-agentapplecomputer-usecomputer-use-agentcontainerizationcuadesktop-automationhacktoberfestlumemacosmanusoperatorswiftvirtualizationvirtualization-frameworkwindowswindows-sandbox
trim cb first steps
Dillon DuPont23102affccd1
diff --git a/docs/content/docs/cuabench/guide/getting-started/first-steps.mdx b/docs/content/docs/cuabench/guide/getting-started/first-steps.mdxindex ad4920b2f8..a2911ee966 100644--- a/docs/content/docs/cuabench/guide/getting-started/first-steps.mdx+++ b/docs/content/docs/cuabench/guide/getting-started/first-steps.mdx@@ -222,32 +222,3 @@ cb run stop <run_id># View traces from a specific runcb trace view <run_id>```--## Advanced: Wait for Completion--By default, runs execute asynchronously. To wait for completion inline:--```bash-# Wait for single task to complete-cb run task tasks/click_button \- --agent cua-agent \- --model anthropic/claude-haiku-4-5 \- --wait--# This blocks until the task completes and shows results immediately-```--## Export Training Data--Export agent trajectories to training datasets:--```bash-# Export with aguvis-stage-1 format-cb dataset build outputs/<run-id> --save-dir datasets/--# Export with gui-r1 format-cb dataset build outputs/<run-id> --mode gui-r1 --save-dir datasets/--# Push to Hugging Face-cb dataset build outputs/<run-id> --push-to-hub --repo-id username/my-dataset-```