Skip to main content

Build Your Own “Self-Healing” Testing Agent

6-hour Masterclass

Build a self-healing agent from the ground up, and master the concepts and techniques to take it to production — no vendor required.

Timetable

8:30 a.m. – 4:30 p.m. Monday 16th

Room

F-,E- & D-Rooms

Artificial Intelligence (AI) Test Automation

Audience

Test automation engineers and developers with Playwright experience in JavaScript/TypeScript.

Required

Laptops, IDE (VSCode, etc.) with node.js.

Key-Learnings

  • Understand how self-healing actually works behind the marketing, including its limits and risks
  • Explore and implement healing strategies step by step — from heuristic fallbacks to LLM-powered fixes.
  • Know when healing is the right call and when a broken test is telling you something important.

It’s not magic, it’s not hard, and you don’t need to buy it

Ever wonder what actually happens when a self-healing agent "heals" your test? It sounds like magic. Vendors love that it sounds like that.

It's not magic. It's something you can build, with a bit of help.

In this tutorial, we're building a self-healing testing agent from scratch - actual working code. We'll start with how locator-based tests break, and how to detect changes on the page. Then we'll explore the heuristics of picking a healing solution - because there's usually more than one. We'll apply changes, run the tests again, and handle what happens when they don't pass.

LLMs join the party - this is the agent era. Layer by layer, you'll understand exactly what's happening behind that curtain. And where it breaks down. When healing hides a real bug. When the right call is to fail, not fix.

You walk away with a working agent and the knowledge to make it yours. You might even save some money on tools.

Key Topics:

  • How locator-based tests break
  • Detecting changes before your test tells you
  • Heuristic healing: choosing between fix candidates
  • Test reconstruction: applying fixes and re-running
  • LLM-powered healing in the agent loop
  • When fixing is actually hiding

Outcomes:

  • Detect UI changes and identify broken locators programmatically
  • Implement multiple healing strategies and evaluate trade-offs
  • Use LLMs as part of an agent healing loop
  • Recognize when self-healing masks real bugs
  • Walk away with a working agent you can extend for your projects

Related Sessions

There are currently no related sessions listed. Please check back once the program is officially released.