February 24-26, 2027
Montreal, Canada
Deterministic testing for non-deterministic AI Assistant
LLM assistant running inside your app breaks a core assumption of e2e testing: the same input can produce different tool calls. I'll show you how I tested an in-app AI assistant using one Gherkin contract and three runners: direct handler calls, deterministic tests using Playwright, and agent-driven browser testing.
Vitaly Skadorva
Intact Financial Corporation
Vitaly is an SDET with 15+ years of experience. He focuses on three areas: AI-driven and agentic testing (Playwright, Cypress), accessibility automation against WCAG, and decomposed test architectures that replace slow E2E suites with parallel layers.
Public speaker: ConFoo (2025), QA or the Highway (2025, 2026).
