Skills
Compile policies into a workflow graph and verify at user-turn boundaries: tau2-bench pass rate 0.42 to 0.62
PolicyGuide stops checking individual actions in isolation and instead compiles organizational policy into workflow graphs, running a proactive verifier at each user-turn boundary that reconciles open requests and returns step-specific remediation along a compliant path. Overall pass on tau2-bench went from 0.42 to 0.62, with telecom the largest gain at 0.19 to 0.61, and the gain held across GPT-5.4, Claude Sonnet 4.6, and Gemini 2.5 Pro. Turn-boundary verification is the part worth copying, since per-action gates cannot see a multi-step procedure going off the rails.
↳ Follow the thread