Agent Readiness Evals Benchmarks Enterprise Adoption

Enterprise Worlds

Executable enterprise environments for measuring operational agents

Enterprise Worlds is an open-source suite of executable enterprise environments for training and evaluating AI agents on realistic, policy-governed operational workflows. Its first released world is ITSMBench, an IT service-management benchmark with persistent state, simulated users, typed tools, and state-based grading.

Recent stories

1 linked story

releasePRIMARY2026-07-29

Enterprise Worlds opens ITSMBench with 93 tools for enterprise agent evals

Enterprise Worlds opened ITSMBench for executable enterprise-agent tasks with persistent state, simulated users, 93 tools, and deterministic grading. The benchmark starts with IT service-management workflows.