AI for QA and testing

AI training programme · 6 modules · 3 Skilledge Hyper labs

89% of organisations pilot GenAI in quality engineering. Only 15% have scaled it.

The 2025 World Quality Report found 89% of organisations piloting or deploying GenAI in quality engineering, but only 15% had scaled it across the company. We think the gap comes from two places. Teams use AI to write more tests rather than better ones. And almost nobody has been trained to test AI itself, which is fast becoming half the job.

At a glance

Who it’s for
Manual and automation testers, SDETs, QA leads, anyone who signs off a release.
Tracks
Quality engineering

Modules

  1. Tests from requirementsTurning user stories into test cases, then asking the AI what you missed.
  2. Test dataGenerating realistic synthetic data without copying production records.
  3. AI-assisted automationPlaywright's agents driving a real browser, and the limits of self-healing.
  4. TriageClustering failures, reading logs, separating flaky tests from real defects.
  5. Testing AI featuresEvals, hallucination checks, red-teaming, and regression testing when a prompt changes.
  6. Where it breaksData privacy, assertions the AI invented, and the review step you can't skip.

Skilledge Hyper lab exercises

Lab designs: what a cohort does in Skilledge Hyper, on mock data.

  • Requirements to suiteA mock e-commerce app and its stories. Generate a suite, then cut it down to the tests that earn their place.
  • Break the chatbotRed-team a mock support bot on a live model, log every failure, and turn them into a reusable eval set.
  • Healer reality checkWe change the app's UI and learners see which tests heal and which pass while checking the wrong thing.

Tools covered

Playwright with its Planner, Generator and Healer test agents over MCP, AI features in Tricentis, mabl, Katalon and Applitools, and general-purpose assistants for test design.

Sources

Related programmes

Want this for your team? Tell us who it’s for and what they need to do differently after it.