At Accenture, I built a Playwright regression framework for a multi-site GenAI chatbot platform. It runs 150+ prompts in about three hours instead of about three days manually, and uses LLM-based evaluation to report verdicts, confidence scores, and response times.
I also validated AWS Bedrock AI agents and CloudIQ checks across SQL Server, Azure SQL, and AWS databases. I standardized GenAI instructions and prompts for 15 services and retested them in the new UAT environment.
Earlier at Accenture, I designed and executed tests for backup, restore, and index-rebuild scheduling services, and developed Selenium automation scripts. I received the Accenture Lantern of Innovation Award and placed third in the Accenture Cebu Prompt-a-thon.
