playground-explorer

What problem does it solve?

Live interactive trajectory exploration and improvement of agent behavior in the Varro playground, enabling researchers to probe observations and actions as they unfold and to propose concrete improvements to tools, prompts, docs, and UI-as-agent-tools.

Core Features & Use Cases

• Live CLI-based probing to diagnose agent behavior in the Varro playground.
• Inspect trajectory artifacts (turns, tool_calls, images) and associated observations to trace decisions and failures.
• Propose concrete improvements to prompts, tools, docs, and UI components, and write findings to data/trajectory/{user_id}/{chat_id}/findings.md.
• Support structured exploration workflows with a clear rubric and validation steps.

Quick Start

Launch a CLI probe by running uv run python -m varro.playground.cli and begin a subject exploration.