The Agentic Quality Summit

Meet the speakers

Engineering leaders from Amazon, American Airlines, Elevance Health, Cypress, and more — sharing what actually works.

Walter Zimmerman

Sr. Developer

Amazon · Former QAE/SDET

About: 8 years building Alexa at Amazon. 17 years in test automation. Built frameworks running millions of tests per month. Hosted Dublin's largest QA meetup (2,000+ members).

Keynote

Scaling Trust, Not Automation

AI fails confidently, not loudly. What that shift means for quality engineering — and why you can't retrofit measurement. Build trust in AI systems while keeping rigorous quality standards.

Deep Barot

Founder & CEO

ContextQA

About: Founder and CEO of ContextQA, the only AI testing platform that truly understands context. Decades of experience across DevOps, full-stack engineering, cloud systems, and large-scale platform development.

Live Demo

Testing AI Agents and Automating the Web with ContextQA

A live, unscripted demo of ContextQA in action. See why traditional testing breaks with autonomous AI agents and how to test agentic systems at scale without flying blind.

Francisco Zenteno

Senior Operations Research Scientist

American Airlines

About: Builds large-scale optimization systems for flight operations. Master's in Computer Science from UC San Diego. Bridges operations research and production-grade engineering.

Topic

Faster Delivery Through Higher Quality

Agentic development for decision-support software. A case study from American Airlines on how quality became the enabler of speed, not a trade-off, in complex operational environments.

Mary Pombares

Transformative Technology Leader

Former Head of QE, Amazon Music

About: Mary reimagines quality as a culture. With 15+ years leading global quality engineering, automation, and digital transformation across healthcare, entertainment, and hospitality, she pairs strategic vision with hands-on delivery.

Featured Talk

Scaling AI Initiatives Across QA

What most organisations get wrong with AI in quality — and what it takes to scale across an enterprise: from isolated pilots to org-wide transformation, without sacrificing velocity.

Praveen Puram

Co-Founder & CEO

Spearsoft

About: A technology entrepreneur and global business leader with 25 years across the USA, UK, and India, leading enterprise transformations across financial services, insurance, healthcare, airlines, and supply chain. Hosts the podcast "Insight with Praveen Puram."

Topic

The Vendor Trap: What to Ask Before You Sign

The hidden traps teams fall into when choosing testing vendors, and the critical questions to ask before signing — so you avoid costly mistakes when evaluating tools, platforms, or AI vendors.

Bhiku Swami

Sr. Director of Technology

Elevance Health (CarelonRx)

About: 26 years across QE, DevOps, Cloud, and AI. Leads 100+ engineers for a $40B+ pharmacy business. Achieved 99.999% availability for cloud-native infrastructure.

Topic

Software Testing using AI Agents

How to leverage AI agents for test generation, execution, and maintenance — moving from script-driven to agent-driven quality engineering at enterprise scale, with lessons from a $40B healthcare org.

Costa Avradopoulos

AI Coach & Trusted Technology Advisor

Avracom · Founder, Agentic Feasibility Framework (AAF)

About: 30+ years in AI, Cloud, IoT, and Mobile. Featured speaker at 70+ global events. President of QAI Atlanta. Delivers up to 50% efficiency gains for clients.

Topic

Agentic Success by Design: A Framework for Feasibility and ROI

Why 95% of AI pilots fail — and how to beat the odds. The Agentic Feasibility Framework (AAF) scoring model for objective prioritization and ROI measurement.

Jenna Beckett

Sr. Developer Relations Engineer

Cypress.io

About: Jenna bridges complex technology and developers through tutorials, livestreams (The Bug Bash), and talks at CypressConf. With a foundation in full-stack development across .NET and JavaScript, she champions testing as the foundation of reliable software.

Topic

MCP for Agentic Testing

How MCP enables structured interaction between AI agents, browsers, CLI tools, and test frameworks — with practical approaches to integrating MCP into your agentic testing workflow.

Harpreet Kaur Gill

Manager, IT

Wipfli Advisory

About: 16+ years across program management, product, quality, and scaled agile. Leads enterprise IT at Wipfli — ERP (Workday), CRM (D365), Power Platform, D&A, M&A integration — and serves as National Vice Chair of Women of Wipfli (WoW).

Topic

Applying Agentic AI for Synthetic Test Data Generation

How agentic AI generates synthetic test data at scale. Why test data is one of the biggest bottlenecks in quality engineering and how AI solves it for enterprise environments.

Irene Thong

Global Technology & Transformation Leader

Global Enterprise

About: An accomplished global technology leader specializing in digital transformation and AI adoption, with extensive experience guiding organizations through major technological shifts.

Closing Keynote

AI in Quality: Why Most Initiatives Stall — and What Leaders Must Do Differently

Why AI quality initiatives fail and the critical strategies leaders must adopt to succeed — with real-world transformation stories and actionable frameworks.

Who should attend

Designed for leaders who own quality outcomes and are ready to lead transformation.

Where it happens