Skip to main content

AI Wrote It. It Looks Perfect. Can You Spot What's Wrong?

25-minute Talk

AI doesn't fail the way we expect. It produces confident, polished, professional-looking mistakes. Your judgment is the only thing standing between "looks great" and a live bug.

Virtual Pass session

Timetable

1:30 p.m. – 2:15 p.m. Thursday 19th

Room

Room E1 - Track 4: Talks

Artificial Intelligence (AI) Test Automation

Audience

Testers, QA engineers, and test leads working with AI tools and AI agents, or about to.

Key-Learnings

  • Name the 3 cognitive traps that make AI output hard to question: automation bias, false fluency, and error anchoring.
  • Spot real AI-generated vulnerabilities in live code before the reveal. Practice critical review under realistic conditions.
  • Build a practical habit: know which parts of AI output to trust, and which parts to always verify.

An interactive detective hunt through real AI security breaches. One case. Three suspects. You're racing to catch what's wrong before I reveal it.

I asked an AI assistant to write a database query. The code came back clean. Well-structured. It passed my first review. It also had a SQL injection vulnerability that could have exposed an entire user database.

My first reaction wasn't "let me check this carefully." It was "this looks really good."

That's still true. But it's not where the danger is anymore. In 2026, the attacks that matter don't come from what the AI wrote. They come from what it read, and what you let it touch.

This session is an interactive detective hunt. Real evidence from real 2026 breaches appears on screen. You're not just watching, you're racing to catch it before I reveal it. One of them, you won't catch. Neither did the people it happened to.

Along the way, we name the traps that make this so hard: automation bias ("the tool generated it, so it's probably fine"), false fluency ("it reads like a pro wrote it"), and error anchoring ("I'll just tweak this and ship it"). I've fallen for all three. Chances are, you have too.

You'll leave with a working mental model for all three traps, a way to read AI tooling evidence that goes past "does it look right," and a practical habit you can use starting Monday, no permission required.

Related Sessions

Virtual Pass session
Thu, Nov 19 • 10:45 a.m. – 11:30 a.m.
Room E1 - Track 4: Talks

25-minute Talk

Artificial Intelligence (AI) Quality Coaching Test Management

Virtual Pass session
Tue, Nov 17 • 11:45 a.m. – 12:30 p.m.
Room D7 - Track 9: Talks

25-minute Talk

Agile Methodologies Artificial Intelligence (AI) Collaboration & Communication

Virtual Pass session
Thu, Nov 19 • 4:45 p.m. – 5:45 p.m.
Room F1+F2+F3 - Plenary

45-minute Keynote

Artificial Intelligence (AI) Other

Thu, Nov 19 • 1:30 p.m. – 4:30 p.m.
Room D3+D4 - Track 7: Workshops

180-minute Workshop

Test Automation