Lee Barnes, Chief Quality Officer at Forte Group, shares why most AI testing pilots fail and how to fix them. He covers scoping, preparing inputs, adding validation guardrails, and evaluating results to decide whether to scale, iterate, or stop.
Hey there. I'm Lee Barnes, Chief Quality Officer at Forte Group, and I'm excited to be back again at Automation Guild. If you've been doing AI augmented testing, you've probably seen the demos. They look amazing. But here's the hard truth. Most AI testing pilots fail, and it's rarely because of the technology. It's because of how we design the pilot itself. In my session Designing an AI Augmented Test Generation Pilot, a Playbook from the trenches, I'll share why pilots stall or disappoint and give you a field tested playbook to make them actually work. We'll cover how to scope your pilot effectively, prepare the right inputs, apply validation guardrails, and evaluate those results to get you to a fast decision on whether to scale, iterate or stop. So whether you're about to launch your first AI testing effort or trying to salvage one that's been struggling, you're going to walk away with practical strategies you can use immediately. So I look forward to seeing you all at Automation Guild 2026.
