Gen AI is a general purpose technology. For testers, context is the king. If context is not engineered well, AI will continue to produce shallow and general results, regardless of how carefully we craft our prompts.

In this talk, we will dive into the practical aspects of context engineering and how it can improve your overall AI assistance.

Many QA teams struggle with test automation adoption. Either their automation isn’t scalable, their test suites become brittle, or they can’t influence the wider team to trust and use the results.

This session will tackle how to build automation that scales with the product and culture, not against it.

LLMs are new and LLMs are scary. The entire way that humanity has built, tested, and shipped software has (seemingly) been flipped on its head with the introduction of LLMs and Generative AI. So how are we supposed to test these things??

This talk seeks to de-magic-ify LLMs and the apps that will be built utilizing this new crazy tech and show that testing these things is not really all that different from what we've all been doing our entire careers.

It is easy to just say "test all the things", but as we all know, that rather quickly becomes unmaintainable. So how do you start from the beginning with a "worth the cost" approach and change over time to continue covering an ever changing product?

This session will give you the techniques for creating strategies and evolving to challenges faced.

Many teams are stuck with outdated or brittle automation strategies that don’t scale, can’t prove ROI, and crumble under tool transitions (e.g., migrating to Playwright).

This session will tackle how to reboot automation with modern, stable, and ROI-driven practices.

Practical, governed AI is no longer optional—it’s the only scalable way to keep quality high while moving faster.

But teams who “AI everything,” burn resources without a ruthless ROI model.

This session delivers the playbook and proof to do it safely in 90 days.

For many years QA / Business Analysts have had to shift through lots of high level documents and identify the business requirements and extract the acceptance criteria.

This sessions aims to teach how to generate test cases from high level documentation in multiple formats.

In agile projects in particular, it is very important to assess software quality as early as possible.

This session aims to lay out all the best practices for API Testing.

Many people who know Selenium or Cypress are encouraged to learn Playwright. We sometimes hear that the best way to learn is to just do it.

Why not have Claude Code right there with you in VS Code helping you learn as you experiment?

It's a pair programmer with you 24/7 as you learn.

Alejandro used it to learn Playwright while also trying the Pop-Up Challenge at candymapper.com.

This session will show you how to use Claude Code as a way to learn new frameworks that feels less daunting.

Every QA team is interested in AI but often don’t know how to start or apply it in daily work.

This session focuses on turning that curiosity into simple, repeatable habits that teams can actually use.

AI outputs are unpredictable and context-sensitive, so standard testing practices don’t always apply.

Many teams don’t know where to begin, which leads to overlooked issues and unexpected behavior in production.

By sharing lessons from a small-scale project, this talk highlights approaches that anyone can try to start testing AI features responsibly.

Many times, QA professionals know they need to learn automation. Yet, taking the first steps to start can feel overwhelming.

Which framework should I choose? What should I automate? How do I know I'm doing it "right"?

Having direction is crucial in these first steps. Knowing where to go and what steps to take can be so helpful when starting in automation.

This session will break down actionable steps that will be helpful in learning how to created automated tests on the job.

In this session, you'll learn how to:

‣ Understand new resilience and performance challenges in MCP-based AI systems.

‣ Learn to integrate AI-assisted observability into traditional load-testing pipelines.

‣ Design adaptive tests that evolve with workload behavior and context drift.

‣ Use open-source telemetry stacks to detect regressions automatically.

‣ Build a continuous-resilience framework for cloud-native, AI-driven platforms.

Release cadence outpaces hand-authored tests; dynamic UIs and headers change faster than scripts.
Traditional frameworks don’t reason, use tools, or self-correct;

GenAI alone doesn’t close the loop.
Security and quality signals are fragmented (browser, network, policy); no autonomous layer connects them.

Teams need operational AI—LLM agents that run workflows (not just generate snippets).

Net: Without agentic patterns (Sense→Plan→Act→Reflect + Memory/Tools), AI remains a helper, not a testing co-worker.

Performance testing provides a complex set of challenges dealing with requirements like scalability, reliability, and speed under varying loads.

Effectively managing these dimensions require you to have deep knowledge of frameworks and provide a large number of inputs to setup and run load tests.

The performance metric outputs are complex and difficult for teams to analyse. This entire process is expensive and time-consuming.

This session will teach you how to use AI to quickly create load tests and analyse test results and get recommendations on how to fix performance bottlenecks in your applications.

Most automation engineers and QA leads struggle to clearly demonstrate the business value of their automation efforts.

When leadership asks, “What’s the ROI of your automation?” the answer often feels vague or purely technical.

This session solves that by giving attendees a practical, repeatable way to calculate, communicate, and prove the ROI of their automation — in terms that win executive trust and investment.

By using principles from Dale Carnegie’s “How to win friends and influence people” - this session will teach testers in guiding their organizations to adopt the right mindset about the value of test automation by walking them through common situations and arguments.

There are times when simple Manual Testing and Smoke Testing isn’t enough.

When you are deploying 8-10 sites with hundreds of pages each, manual testing can allow you to check a dozen pages or so. Smoke Testing covers the critical paths.

This session will help you reduce the pressure of manual validation post-deployment.

Many teams build large automation suites without a roadmap, leading to flakiness, slow feedback, and unclear value.

Leaders struggle to prove the ROI of automation or decide what to prioritize next. Testers often focus only on adding more tests instead of improving stability, speed, or business impact.

Without a maturity model, teams lack a shared language to assess progress and align on growth goals.

This session will give teams a maturity framework -- create a shared roadmap: a way to assess current state, identify gaps, and prioritize improvements that align automation with business goals.

Most testing initiatives fail not because the solution is wrong, but because the business problem wasn’t framed—or sold—correctly.

In this talk, Federico will show how to connect the dots from messy business challenges to clear quality engineering outcomes that stakeholders actually support.

A lot of people don't know how to create an effective test strategy (or even that they need to) and often resort to only doing the bare minimum or trying to shoehorn their needs into the tools they have available.

This hands-on workshop session will show how to effectively use AI to create effective and efficient test strategies that work.

Universal frustration: Every automation engineer has once said "But it works on my machine!" When tests fail unpredictably in CI, teams lose confidence in their automation.

Many test automation engineers excel at writing tests but lack deep knowledge of CI environments, containerization, and infrastructure differences.

This session aims to solve that problem.