Workflow risk guardrails — UX audit rules

Rule handbook metadata

Rule: AI.APP.WORKFLOW_RISK_GUARDRAILS · lane ai
Page status: current
page_version: 6cc82c17284e7c711673340a0ee1f4172fb52629c2ece866872f84f3b1e79946
generated_at: 2026-08-13T02:31:57.132Z
registry_fingerprint: aef1de6082cf0f50d463783c843dee0ffb9132fbd5ed4ea6e5bb3f031f359c72

How this rule is fixed

This is an AI-enabled rule. Pass/fail requires model judgment; there is no deterministic fixer in the pilot registry.

Harness: invoke-ai-ruleset-harness.sh runs design-rules/ai/run-design-ai-rule.sh on the Before fixture and expects findings with matching principleId.
Remediation: Cursor agent plans from forge-ux-remediation.plan.md after sitewide audit — not handbook After copy.

Detection module: docs/design/ux-audit/ai-enabled-design-principles.md#ai-app-workflow-risk-guardrails. Scroll down for Before / After examples and Evidence and remediation steps.

Purpose

Destructive or irreversible actions have proportionate guardrails. Judgment overlay for AI.APP.WORKFLOW_RISK_GUARDRAILS.

Required finding metadata

Each finding must include: principleId, severity, deterministicCoverage, candidateDeterministicRule, screenshotOrDomEvidence, hashesOrContractsAffected, confidence, recommendedFixScope, sourceFilesLikelyAffected.