Where agentic workflows actually earn their keep in a real QA pipeline — and the two places they quietly fail.
The four control surfaces to set up before an agent touches production: scope, evaluation, failure cataloguing, human-in-the-loop.
Patterns for flaky-test triage, regression pruning, and visual-diff arbitration with receipts from three production systems.
A reference architecture you can take back to Monday’s sprint planning, plus the metrics that prove it’s working.
VP of Engineering
“20+ years in enterprise software and cloud platforms — design, development, testing, and program leadership. For the past decade, I’ve led Quality Engineering and Product Development across globally distributed teams spanning the US, Brazil, China, and India.
My recent focus is AI transformation in quality engineering — not as a concept, but as something I’ve built. This includes architecting agentic test frameworks powered by LLMs, integrating AI evaluation pipelines into CI/CD, and redefining what quality engineering looks like when AI drives the development lifecycle”
Soumya Mukherjee is a Senior Principal Engineer at MAANG, where he leads a supply chain ML team building AI systems at global scale, spanning forecasting, RAG pipelines, explainability, and local LLM deployments. With 18+ years in the industry, he pivoted from Engineering into Machine Learning and AI, along the way starting his own consulting firm and building technology at Morgan Stanley. He is an Amazon-published author and a PhD researcher at IIT Patna working on explainable AI. A regular speaker at various conferences, he has mentored 500+ engineers across his career.
One pass, every talk, no parallel tracks. Super Early Bird ends when the next 200 seats are gone.
Join our community of testers and start your journey
Just fill the form and get an exclusive discount too.