Even with modern frameworks like Selenium, Playwright, or Cypress, most testers still deal with fragile locators, flaky scripts, and too much time spent on test upkeep. This session introduces a smarter way forward: Agentic AI that works more like a human — no scripts, no frameworks, and no maintenance overhead.

• Understanding runtime agentic AI test automation
• Being able to articulate the benefits and differences between a co-pilot approach to test automation and a runtime agentic AI approach

Mainframe environments are complex, interconnected, and mission-critical—making them ideal candidates for AI-driven automation. But not all AI automation is created equal. As enterprises move from traditional automation toward intelligent autonomy, understanding the distinction between Agentic Workflows and Agentic Agents becomes essential.

This session will explore how these two approaches are being applied to transform the developer experience:

• How Agentic Workflows bring structure and predictability by guiding tasks through rule-based and AI-enhanced flows
• How Agentic Agents go further—acting as goal-driven collaborators that learn, reason, and make decisions autonomously across DevOps, AIOps, and system management tasks
• Real-world examples of how organizations are applying both to reduce manual effort, mitigate risk, and accelerate innovation
• Steps to go to the next level of AI maturity for your development and test process

Whether you’re modernizing core applications or transforming mainframe operations, this session will help you harness the right kind of intelligence at the right time—with practical insights to guide your next move.

• What are AI Agents, Agentic Workflows, and MCP Servers
• How they can help you get more out of AI
• How developer workflows can be enhanced by using Agents
• How to start using them for your Developers

Drawing on real-world examples, we will look at how teams are successfully using low-code/no-code tools, adopting test generation via AI, and embedding automation earlier in the development lifecycle.

• Key barriers to democratization and how to address them
• Governance and guardrails that empower non-QA contributors without risking test debt
• Tools and frameworks that support inclusive automation practices
• Cultural enablers that drive adoption and long-term success

A comprehensive .NET testing framework specifically designed to implement continuous testing strategies for microservices architectures, enabling organizations to fast-track their ability to deliver high-quality software with reduced time-to-market and lower operational risk.

• ⁠Multi-Level Testing Strategy

Supports the complete testing pyramid: Functional, Integration and EndToEnd

Enables testing at every stage of the CI/CD pipeline from pre-commit to post-production deployment

• Service Virtualization & Isolation

Built-in service virtualization for testing microservices in complete isolation

Eliminates dependencies on external services during testing

Enables comprehensive scenario and edge case testing

• Infrastructure Automation

Automated AWS infrastructure simulation for local development

Docker-based test environment provisioning

Seamless database management with Flyway migration support

• Developer-Centric Design

In-memory hosting of System Under Test (SUT) for blazing-fast test execution

BDD-style test writing aligned with acceptance criteria

Robust test data management and automated report generation

• This framework represents a shift from reactive quality control to proactive quality engineering, making it particularly valuable for
• Enterprises seeking to reduce technical debt and improve software reliability
• Development teams looking to increase deployment frequency while maintaining quality
• Teams adopting DevOps and continuous delivery practices
• Cost Reduction: Early defect detection saves exponentially more than production fixes
• Service Isolation: Test microservices independently without external dependencies
• Infrastructure as Code: Automated AWS simulation and Docker provisioning

Imagine describing what you need in plain language—and having intelligent agents build it for you. The session will explore how GenAI is revolutionizing automation by turning natural language prompts into end-to-end processes across QA and RPA workflows.

The session will demonstrate real-world examples of prompt-driven agents creating tests, workflows, and exception-handling routines—showcasing how GenAI is making automation smarter, faster, and more accessible for everyone. Whether you’re streamlining testing or scaling bots, this session will leave you with practical ways to move from “idea to execution at the speed of a prompt”

• GenAI bridges the gap between humans and automation tools—no more translating requirements into scripts manually.

• QA and RPA teams can now create and maintain automation faster, with fewer handoffs and more resilience.

• Prompt engineering is the new automation superpower—understanding how to frame a request will be key.

• Agentic automation enables systems to adapt and evolve, reducing the burden of test and bot maintenance.

• The future of automation is inclusive—business users, testers, and developers can co-create with AI.

This talk shares hands-on case studies from my career in building and scaling test automation in different industries. Instead of abstract principles, I’ll walk through concrete examples of automation projects—what worked well, what failed, and the lessons learned. Takeaways: Practical Lessons – Learn what worked and what failed from real automation projects. Framework Decisions in Context – See how framework choice and POM affected maintainability. Handling Challenges – Approaches to flaky tests, regression bottlenecks, and tool mismatches. Measurable Impact – Case studies showing reductions in regression time and defect leakage. Actionable Insights – Concrete do’s and don’ts that attendees can apply in their own teams.

Attendees will see how framework selection, design patterns like Page Object Model, and test strategy decisions played out in practice. I’ll cover challenges such as flaky tests, long regression cycles, and tool misalignment, and show the technical solutions we used—from test data management to integrating automation in CI/CD pipelines. Each case study will highlight before vs. after metrics (e.g., regression time, defect leakage, release cadence) to prove impact. Alongside successes, I’ll share missteps and what I’d do differently today. This session is highly practical and technical, aimed at helping teams avoid common pitfalls and accelerate their own automation journey.

Being proactive is shifting left and selling QA is doing the same in my opinion. it is all about moving further left getting in earlier to process and helping teams improve their quality before it even gets to being made as a product. QA should be at the design table to help with Accessibility, and work with UX to ensure it is logical and to help with the quality.

• learning to implement automation farther up the chain
• See actual slides that help you move quality into different groups
• Case studies that show how my teams have shifted left
• A real life example of company that didn’t focus on Quality or shifting left and the problems they were experiencing

I’m currently the Senior Director of Engineering at Cisco, leading key functions within the Duo Security Business Unit, including Site Reliability Engineering (SRE), Quality Engineering, and market access (FedRAMP/ISMAP compliance and global expansion).

The Quality Engineering team spans test automation, performance engineering, developer tooling, and PMO. A major focus of my role is mentoring and growing our team—now 115 strong, including 2 Directors and a dedicated PMO—since joining as the first member in 2016. Hiring and building high-performing teams has been a core and rewarding part of my journey.

Outside Cisco, I serve on the board of AquilaTest.ai, an AI-powered codeless test automation platform helping teams ship high-quality software faster through predictive and prescriptive analytics.

At Duo, we release software every two weeks and embed quality directly into the development process. Our SRE teams ensure service reliability, security, and scalability across regions including the US, UK, India, and Australia, with a strong emphasis on automation and operational excellence.