Microsoft's ThinkingBox ships as an OpenEnv environment
ThinkingBox now runs as an OpenEnv environment: it simulates a customer, gives the agent MCP tools over a real database, and judges tasks by what changed in the database rather than the agent's final message, with a 507-task ThinkingBox-Bench.
ThinkingBox from @Microsoft is now available as an OpenEnv env! > ThinkingBox is a sandbox for testing agents on business workflows. it simulates a customer, gives the agent MCP tools over a real database, and at the end checks what changed in that database instead of trusting the agent's last message > ThinkingBox-Bench is the benchmark built on it: 507 tasks across retail, insurance, travel, banking and consulting > the OpenEnv env runs each task as an episode in its own isolated backend and returns a pass/fail reward from those checks https://huggingface.co/blog/microsoft/thinkingbox