New Episodes Weekly

The Agentic Quality
Podcast

Engineering leaders, developers, and quality professionals discuss how AI is reshaping software quality — from test strategy and developer workflows to trust, scale, and decision-making. No hype. Real stories, real trade-offs, practical takeaways.

Apply to be a Guest

Meet the Host

Tatyana Arbouzova

Tatyana brings deep expertise in quality engineering, AI-driven systems, and engineering leadership. She's passionate about helping teams navigate the intersection of automation, intelligence, and human judgment — building systems that scale without sacrificing trust or rigor.

Why This Exists

Real-world conversations about AI,
quality, and decision-making

Teams are moving fast, systems are complex, and traditional test automation often creates noise instead of confidence.

Who We Talk To

Engineering leaders, developers, and quality practitioners navigating real-world AI adoption in software teams at companies like Amazon, Slalom, Fox, Forbes, and more.

What We Focus On

How AI changes decisions, not just tools. Honest discussions on trade-offs and real failures. No generic "AI will change everything" — just what actually works in production.

Core Themes

Trust in automation, signal vs. noise in testing, scaling quality without losing rigor, and agentic systems with human-in-the-loop oversight.

What You'll Walk Away With

01

Evaluation Skills

Better ways to evaluate AI in testing — beyond demos and vendor promises.

02

Practical Approaches

Methods to increase trust and reduce noise in automated testing pipelines.

03

Alignment Language

Ways to align quality work with business outcomes that leadership understands.

04

Clear Path Forward

From automation → augmentation → agentic quality. A roadmap for modern QA.

Season 2

9 Episodes

Season 2 · Episode 1

How One QA Leader Cut Regression Testing from 2 Weeks to 2 Days with Multi-Agent AI

"Starting accuracy of 60–65% can climb to 90% within months once the LLM is fed the right application context."

Anupama Khatam

Director of Software Quality Assurance, NCQA

Season 2 · Episode 2

How Microsoft Tests AI That Never Gives the Same Answer Twice

"AI is pumping in so much amount of code... the amount of testing that needs to be done will definitely increase a lot."

Deepanjan Bhol

Senior Principal Software Engineering, Microsoft

Season 2 · Episode 3

Why AI Isn't Making Your Team Ship Faster

"AI is a powerful accelerant - but you have to have something worth accelerating. Perfect tools inside a broken process achieve nothing."

Nishadhi Nikalandawatte

Director, Market Solutions, Slalom

Season 2 · Episode 4

How Oracle Is Driving AI Adoption Across 150,000+ Employees

"We are not selling AI. We are helping people solve problems."

Max Xiao

Sr Principal Technical Program Manager, Oracle

Season 2 · Episode 5

How Amazon Ships with AI Agents in the Loop

"AI shifts QA roles from manual testing to meta-orchestrating: defining rubrics and validating AI evaluation systems "

Naman Rajpal

Senior Software Development Engineer, Amazon

Season 2 · Episode 6

Why the Future of QA Is "Trust Engineering"

"Most teams are still measuring how many test cases AI produced, when they should be asking whether product quality actually improved."

Mary Pombares

Head of Quality Engineering, Ascension, Ex Amazon

Season 2 · Episode 7

Why AI Won't Replace QA, It Will Transform It

"We are solving creation, but verification is the next challenge."

Jairo Gutierrez

Director of Quality Engineering, Slalom

Season 2 · Episode 8

How AI Built a Mobile Test Framework in 3 Weeks

"The gap between AI productivity and AI trust is closing fast. Next year, it'll be under 10%."

Suneet Malhotra

Sr. Manager – Test Engineering, Motorola

Season 2 · Episode 9

How AI Is Transforming Enterprise QA

"Don't start with the AI tool. Start with the problem you're trying to solve."

Dave Sommer

Vice President of Quality Engineering, Korn Ferry

Season 2 · Episode 10

Can Non-Technical Teams Build Production AI Systems?

"The only technical skill AI requires is clear communication."

Aaron Patrick Doherty

Head of AI & RevOps, Chowly

Season 2 · Episode 11

How Can AI Agents Make Your Deployment Pipeline 10x More Productive?

"Design for the constraint you haven't hit yet, ask what breaks at 10x, and build for it before the pressure arrives."

Vasu Raj Jain

Senior Software Engineer & Engineering Lead, Amazon Ads

Season 1

15 Episodes

Episode 1

Quality as an Operating System: From Test Counts to Trust Checkpoints

Rethinking quality metrics and building trust at scale.

Nishadhi Nikalandawatte

Director of Quality, Slalom

Episode 2

Quality at High Velocity: Keeping Testing Principles in Rapid Delivery

Maintaining quality principles while shipping fast in modern development.

Deep Barot

CEO, ContextQA

Episode 3

Using AI Without Losing Critical Thinking: A Developer's View

How developers stay sharp while leveraging AI tools in their daily workflow.

Walter Zimerman

Software Developer, Amazon

Episode 4

AI Won't Replace QA: It Amplifies the Quality Mindset

Use AI to accelerate repeatable work; keep humans on judgment and culture.

Priyamvada Govil

Senior Quality Engineering Leader

Episode 5

From Automation to Agentic Testing

Self-healing tests are achievable when AI understands context and intent.

Greg Goldshteyn

QA Manager, Fox Networks

Episode 6

AI in FinTech Testing: High-Stakes Quality, Compliance, and the New Role of SDETs

Testing in high-stakes FinTech systems where mistakes affect real money and trust.

Ravi Subramanian

Software Developer, Amazon

Episode 7

Automation ≠ Quality: How to Measure Test Automation Effectiveness

Automation is a capability, not a quality strategy. Quality is about risk, customer experience, and release confidence.

Alekhya Guduri

Director of Engineering, Indeed

Episode 8

Observability-Led Quality Engineering: Using AI to Turn Production Data into Better Testing

AI helps analyze large-scale production data and reduce noise.

Shrish Ashtaputre

Senior Technical Director, Calsoft

Episode 9

AI in Healthcare Quality: From Rule Engines to Responsible Adoption

AI helps generate skeleton test cases and uncover edge scenarios humans may miss.

Radhika Naik

Quality Engineering Leader, Apexon

Episode 10

Multi-Agent Engineering: Building Disagreeing Systems for Higher Quality

AI is making engineers faster — but it's not automatically making teams better.

Devashish Meena

Senior Director, Esper

Episode 11

AI in Software Delivery: Lessons from Forbes' Platform Stability Team

Forbes treats AI like a junior dev — review everything, trust nothing.

Ronak Ray

VP of Platform Stability & AI Ops, Forbes

Episode 12

Quality Engineers as Risk Intelligence Experts: AI, Finance Systems, and the Future of Testing

The role of QA is evolving toward risk intelligence engineering.

Tanvi Mittal

Quality Engineering Leader

Episode 13

QA Is No Longer About Testing — It's About Trust, Speed, and AI

Don't chase shiny tools — understand your problem first, then find the solution.

Jackie Namanda

Technology & Quality Engineering Leader

Episode 14

QA in Clinical Trials: When a Bug Can Affect a Patient

AI is your best friend. The faster you bond with it, the faster you stop being a tester and start being a strategist.

Rohit Singh Raja

Quality Engineering Leader

Episode 15

QA's AI Shift: From Pass/Fail to Grading Reasoning

Start with a baseline before adopting AI to measure real ROI.

Stacy Kirk & Brittany Stewart

QualityWorks Consulting Group

Join the Conversation

Want to be a Guest?

We're always looking for engineering leaders and practitioners with real-world experience navigating quality, scale, and AI. Share your story with thousands of practitioners.

Apply to be a Guest