2 docs tagged with "rule-based"

When an AI worker completes a task, how do you know whether the work was any good? Eval scorers provide structured quality assessment of agent work — each scorer examines a completed run and produces a numeric score with optional reasoning.

Before an AI worker touches your codebase — and again after it finishes — guardrails run automated safety checks to catch problems early. They act as gatekeepers: a guardrail can warn you about a potential issue or block a dispatch entirely.