• Develop comprehensive test strategies: Create and maintain test plans covering functional, performance, and regression testing for AI agents and automation workflows. • Build and maintain automated test frameworks: Develop and maintain automated test scripts/frameworks to ensure bot responses and workflow outputs remain accurate, consistent, and reliable over time. • Build and maintain test assets: Create/curate golden conversation sets, synthetic test data, evaluation rubrics, and regression suites to measure quality over time. • Validate AI agent safety and reliability: Test tool-calling end-to-end (tool selection, parameter mapping, sequencing, retries/timeouts, error handling, and recovery), including negative/edge cases; confirm outputs align to business rules and document risk mitigations. • Test integration/workflow integrity: Validate API contracts, data transformations, and downstream impacts (idempotency, duplicate prevention, partial failures, and latency) across environments. • Manage defects through resolution: Identify, log, prioritize, and track defects; partner with developers to reproduce issues and validate fixes. • Provide release certification: Deliver final quality sign-off prior to production release, ensuring defined acceptance criteria and quality standards are met. • Align on acceptance criteria: Partner with Business Analysts to ensure user stories include clear, testable acceptance criteria and that test coverage maps to requirements. • Document testing and metrics: Maintain test cases, data, results, and quality metrics; communicate outcomes and risks. • Participate in Agile ceremonies: Engage in planning, grooming, standups, and retrospectives to embed quality throughout delivery. • Drive continuous improvement: Identify opportunities to improve automation coverage, testing effectiveness, and quality practices.