Examples of playbooks turned into runnable agent tests.
Each example shows how a business workflow becomes actors, tools, constraints, scenarios, and scorecards an agent must pass before touching real users.
Voice Agent Testing
Voice Operations Agent Test Suite
A draft suite for testing AI voice agents across consent, task completion, policy boundaries, and call-quality outcomes.
Security Operations Agents
Security Operations Agent Test Suite
A draft suite for security agents that triage alerts, collect evidence, classify severity, and route containment safely.
Financial Crime Compliance Agents
Financial Compliance Agent Test Suite
A draft suite for compliance agents that review KYC, AML, adverse media, and financial-crime exceptions.
IT Service Management Agents
IT Service Management Agent Test Suite
A draft suite for IT-service agents that resolve employee requests while respecting identity, permissions, and approval gates.
Computer-Use Agents
Computer-Use Agent Test Suite
A draft suite for computer-use agents that need reproducible desktop or browser tasks with trajectory-level checks.
Software Engineering Agents
Software Engineering Agent Test Suite
A draft suite for coding agents where repo state, tests, patch quality, and non-regression behavior matter.