​AI is bringing a new set of questions into software testing.

​How do you test an application when the same input can produce different outputs? How do you decide whether an AI response is acceptable? And how can AI help teams build and maintain automation without adding more complexity?

​At The Test Tribe Berlin Meetup, two experienced Quality Engineers will share how they are working through these challenges in real projects. The sessions will cover AI-assisted Playwright automation, LLM evaluation, quality gates, CI/CD integration, and lessons from testing AI systems in regulated environments.

​Event Details

​Date: 26 August 2026

​Time: 6:00 PM - 9:00 PM CET

​Venue: SumUp, Entrance via Lange Straße, Koppenstraße 8, 10243 Berlin, Germany

​What's on the Agenda?

​Session 1: Shift Fast, Test Smart: Full-Stack Playwright Automation Powered by Gemini

​Speaker: Smita Mehta, QA Lead at Schwarz

​Maintaining separate UI and API automation frameworks can slow teams down, especially when older Selenium suites also need to be migrated.

​In this session, Smita will show how UI and API testing can be brought together in a Playwright-based framework. She will also demonstrate how Gemini Code Assist can support test development, Selenium migration, debugging, and day-to-day automation work.

​The session will focus on practical ways to create tests faster while keeping the framework easier to maintain as the application changes.

​Session 2: AI and LLM Validation in Real-World Systems

​Speaker: Osama Hammad, Senior Software Testing Engineer at PaxeraHealth

​Traditional testing usually works with clear expected results. AI systems are different. Their outputs can vary, and deciding whether a response is correct often requires more than a simple pass or fail check.

​Osama will share lessons from testing AI-powered medical imaging and healthcare systems. He will explain how teams can create evaluation frameworks, define quality gates, add AI validation to CI/CD pipelines, and work within requirements such as the EU AI Act.

​Although the examples come from healthcare, the approaches discussed will be useful for anyone testing AI or LLM-based applications across different industries.

​How This Meetup Solves Your Problem

​This meetup is for you if your team is currently testing AI features, exploring LLM-based applications, or trying to improve an existing automation setup.

​You will learn:

• ​How to evaluate AI outputs when traditional assertions are not enough

• ​How Quality Engineers can test LLM-based applications

• ​How evaluation checks can become part of a CI/CD pipeline

• ​How Playwright can support both UI and API automation

• ​How AI-assisted development can help with test creation, migration, and debugging

• ​What testing AI systems in a regulated environment can teach teams in other industries

​Why You Should Show Up

​Both sessions are based on work being done by practitioners, not just high-level discussion.

​You will get a closer look at the tools, decisions, and testing approaches behind modern automation and AI validation. You will also have the chance to ask questions, compare experiences, and meet testers, SDETs, automation engineers, and technology leaders from Berlin's software testing community.

​Come for the sessions, stay for the conversations, and leave with ideas you can take back to your own team.

​Become a Speaker at The Test Tribe events:

​Wish to share your insights with the community at a future event? Submit your talk idea here and our team will get back to you if the idea resonates with them too.

​​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