Skip to content

Details

4th Europe Huddle - Explore Before You Automate: Building an AI Agent for Automation Readiness

What if your AI agent could explore an application before deciding what should be automated?
This session takes a practical look at using AI and agentic workflows to bring exploratory testing before automation. You’ll see how an agent can combine a user story, project context, QA testing heuristics, and Playwright MCP to explore a running application and identify what is actually ready for automation.
Rather than allowing AI to make assumptions, the approach keeps the QA engineer in control — surfacing risks, edge cases, accessibility observations, locator stability, and unanswered questions before automation begins.

Event Details

  • Date: 16 October 2026
  • Time: 04:00 PM CET
  • Venue: Online - Zoom Webinar

Session - Explore Before You Automate: Building an AI Agent for Automation Readiness

Speaker: Pranita Panse, SDET at UIS, University of Cambridge

The session will demonstrate how to build an exploratory testing agent using Playwright MCP and a reusable Exploratory Testing Skill.
Starting with a user story and available project context, the agent explores the running application and evaluates:

  • Risks, validations, positive and negative paths, and edge cases.
  • Accessibility observations and locator stability.
  • Testability using roles, labels, accessibility information, and maintainable Playwright locators.
  • Missing domain knowledge or unclear requirements, surfaced as open questions rather than assumptions.
  • Potential BDD and automation candidates based on what the exploration reveals.

The exploration ultimately produces an automation-readiness report to help the QA engineer decide what should be automated, what needs clarification, and what is better kept exploratory.

How This Huddle Solves Your Problem

  • Automating too early? Explore the application first and identify what is actually ready for automation.
  • AI makes assumptions when requirements are unclear? Use open questions to surface gaps instead of letting the agent fill them in.
  • Automation becomes fragile because of poor locators? Evaluate locator stability and testability during exploration.
  • Not sure what should be automated? Turn exploratory findings into meaningful BDD and automation candidates.

Why Show Up on 16 October?

  • Because automation shouldn't begin before you understand what you're automating.
  • Because AI can support exploratory testing without replacing the QA engineer's judgment.
  • Because testability and locator stability can be considered before automation creates technical debt.
  • Because you'll see how Playwright MCP and reusable testing skills can work together in an agentic workflow.
  • Because the goal isn't to automate everything — it's to make better automation decisions.

Become a Speaker at The Test Tribe Events

Have a testing, quality engineering, automation, or AI story worth sharing with the community?
Submit your talk here and get a chance to speak at an upcoming The Test Tribe event.

About The Test Tribe

The Test Tribe is the world's largest software testing community, empowering testers globally since 2018. With 850+ events and 165K+ members across 140+ countries, we bring testers together to learn, grow, and connect through meetups, conferences, cohorts, masterclasses, and more.

By RSVPing, you agree to our Terms and Conditions and Privacy Policy and consent to be contacted by The Test Tribe and our event partners.

You may also like