Nordic Testing Days 2026

This full-day, hands-on tutorial dives into test automation using the Model Context Protocol (MCP) and AI agents. Participants will first master the MCP architecture, the standardized foundation for AI-driven applications.

The core of the tutorial focuses on Playwright's AI Agents (Planner, Generator, Healer). You will learn to leverage these agents to:

• Intelligently discover and map application test surfaces (Planner).
• Automatically generate executable Playwright code from natural language specifications (Generator).
• Implement self-healing mechanisms to automatically detect and repair broken tests after UI changes (Healer).

The session covers integration techniques, including connecting MCP with GitHub Copilot for an issue-to-implementation workflow, and best practices for production-ready, CI/CD-integrated test suites.

Prerequisites:

• Basic understanding of JavaScript/TypeScript
• Familiarity with web testing concepts
• Node.js 18+ installed
• VS Code or similar IDE

Tutorial Objectives:
By the end of this tutorial, participants will be able to:

1. Understand the Model Context Protocol (MCP) architecture and its role in AI-driven automation
2. Set up and configure MCP Playwright servers in multiple environments
3. Leverage AI agents (Planner, Generator, Healer) for test automation
4. Build intelligent, self-healing test automation frameworks
5. Integrate MCP with GitHub Copilot and other AI tools
6. Implement best practices for production-ready test automation

Tutorial Agenda
Morning Session (9:00 AM - 12:30 PM)

• 9:00 - 9:30 AM: Welcome & Tutorial Introduction
  • Participant introductions and icebreaker
  • Tutorial objectives and expected outcomes
  • Overview of the day's schedule
  • Environment setup verification
• 9:30 - 10:45 AM: Module 1 - Understanding MCP (Model Context Protocol)
  • What is MCP and why it matters
  • The evolution from custom integrations to standardized protocols
  • MCP as the "USB-C for AI applications"
  • MCP Architecture deep dive
    • Client-Server architecture
    • MCP Host, Client, and Server relationships
    • Data layer: JSON-RPC 2.0 protocol
    • Transport layer: stdio, SSE, WebSockets
  • MCP vs traditional approaches (ChatGPT plugins, custom APIs)
  • Real-world use cases and success stories
  • Hands-on Exercise 1:
    • Setting up your first MCP server
    • Configuring Claude Desktop/VS Code with MCP
    • Testing basic MCP connectivity
  • Resources Provided:
    • MCP architecture diagrams
    • Configuration templates
    • Troubleshooting guide
• 10:45 - 11:00 AM: Coffee Break
• 11:00 AM - 12:30 PM: Module 2 - Playwright MCP Fundamentals
  • Introduction to Playwright MCP Server
  • Microsoft's official implementation vs community alternatives
  • Key features: accessibility tree usage, deterministic actions
  • Supported capabilities: vision, PDF handling
  • MCP Server architecture for Playwright
  • Browser automation via MCP protocol
  • Tools, Resources, and Prompts in MCP context
  • Storage modes: persistent vs isolated profiles
  • Demo Session:
    • Installing Playwright MCP: npx @playwright/mcp@latest
    • Configuration options and arguments
    • Connecting MCP to different clients (Claude Desktop, VS Code, Cursor)
    • Live demonstration of browser automation via MCP
  • Hands-on Exercise 2:
    • Configure Playwright MCP in your development environment
    • Create your first AI-driven browser automation
    • Use natural language prompts to navigate and interact with a demo website
    • Capture and analyze accessibility snapshots
    • Challenge: Automate a simple e-commerce flow (browse → add to cart → checkout) using only natural language prompts through MCP.

Lunch Break (12:30 - 1:30 PM)
Afternoon Session (1:30 PM - 5:00 PM)

• 1:30 - 3:00 PM: Module 3 - Playwright AI Agents
  • Introduction to Playwright Test Agents
  • The three agents: Planner, Generator, Healer
  • Agent workflows and lifecycle
  • Planner Agent: Intelligent test discovery
    • How it explores applications
    • Generating comprehensive test plans
  • Generator Agent: Automated test creation
    • Converting test plans to Playwright code
    • Natural language to code translation
  • Healer Agent: Self-healing tests
    • Detecting and fixing broken tests
    • Automatic locator updates
    • Handling UI changes
  • Demo Session:
    • Setting up Playwright Agents: npx @playwright/test init-agents
    • Live demo: Planner agent exploring a web application
    • Live demo: Generator creating tests from specifications
    • Live demo: Healer fixing failing tests after UI changes
  • Hands-on Exercise 3:
    • Initialize agents in your project
    • Use Planner agent to explore a sample application
    • Generate test specs in Markdown format
    • Convert specs to executable Playwright tests with Generator
    • Introduce breaking changes and use Healer to repair tests
  • Group Activity: Teams work on different sections of an e-commerce application, comparing agent-generated tests vs manually written tests.
• 3:00 - 3:15 PM: Coffee Break
• 3:15 - 5:00 PM: Module 4 - Advanced Integration & Best Practices
  • Integrating MCP with GitHub Copilot Coding Agent
    • How Copilot uses Playwright MCP
    • Verifying code changes in real browsers
    • Issue-to-implementation workflow
  • Advanced MCP features
    • Custom MCP servers for specific needs
    • Multi-tool workflows (MCP + web search + internal tools)
    • Security considerations and sandboxing
  • Best practices for production deployments
    • Test organization and structure
    • Page Object Model with AI-generated tests
    • CI/CD integration (GitHub Actions, Docker)
    • Test data management and fixtures
    • Handling flaky tests with AI assistance

Testers often need custom tools - data generators, mock services, internal dashboards, or CI helpers - but building them traditionally requires significant development effort and prioritization. With modern AI-assisted coding, we can now prototype and build these tools themselves, minimizing both engineering and maintenance efforts. In this session, I’ll show real examples of using vibe-coding to create internal testing workflows, interfaces, and CI/CD helpers. I’ll focus on where AI significantly accelerates development, where it introduces risks, and how to apply guardrails to keep these tools maintainable, secure and trustworthy.Rather than promoting “AI replaces engineers,” this talk presents AI as a practical productivity amplifier for experienced testers who understand their systems and constraints.


Key takeaways:

1. How to design and build tester-owned tools using vibe-coding without creating technical debtAttendees will learn how to approach AI-assisted development of internal testing tools (data generators, mock services, dashboards, CI helpers) with clear ownership boundaries, architectural decisions, and sustainability in mind.
2. A realistic mental model for AI-assisted coding in testing workflowsParticipants will gain a clear understanding of where vibe-coding provides real leverage for experienced testers, where it breaks down, and how to critically evaluate AI-generated code instead of blindly trusting it.
3. Practical guardrails for security, maintainability, and long-term useAttendees will leave with concrete strategies for applying constraints - such as validation, code structure, reviews, and documentation - to ensure AI-built tools remain trustworthy, auditable, and safe to evolve over time.

SummarySecurity testing sounds like it might be best left to the “experts”, whoever they are, but I will share how we can include it in our day-to-day testing. From exploratory testing to API and automated testing, there are things that we can and should be doing.Through this workshop we will learn about the scope of security testing, find out about the automated tools available and then spend some time practicing basic security testing techniques like SQL Injection, Insecure Direct Object Reference and using browser developer tools.Setup- Attendees will need to bring a laptop or pair up. Any browser is fine but Chrome recommended. - Screen & HDMI/equivalent for presenting slide & demos.ActivitiesFor a 2 hour workshop:- IDOR / URL manipulation- Bypassing UI using developer tools- Cross site scripting (XSS)- SQL injectionIf a 4 hour workshop is preferred, I can add in additional activities including analysing session data and a Capture the Flag exercise.

Key takeaways:

1. Recognise that security testing is something that you can & should be doing
2. Identify the "low hanging fruit" security bugs in software
3. Execute basic penetration tests against an online system

ISO 25010, not the topic that ignites the fire in our test-hearts, right? Non-functional testing and quality characteristics are often seen as a hassle and don’t get the attention they deserve. So, what can we do to make non-functional testing fun? Let’s do something completely different!How about we make a short film script about a quality characteristic of our choice? Let's go!  Pre-screening: We show you some examples of famous films and what they can teach us about quality characteristics. We also explain what these quality characteristics mean and why they are important.   Take 1: Welcome to Testlywood, film crew! Let’s get acquainted. Create your production company and distribute the roles in your film-crew. We will explain you the various roles, such as director, art director, movie critic and others.   Take 2:  Camera, ready, action! In this round you will use a mix of generative AI & human creativity to create your filmscript and upload it to Github. Present it to the group in a 1-minute pitch. The movie critics from the other teams will provide feedback at the end of this take.  Take 3:  Use the feedback movie critics feedback to finalize your filmscript. Your script is done, splendid!  But the audiences still need to know your movie exists. Design a film poster that really captivates your core message. Submit both your filmscript and the poster as an entry for the ceremonies. Post-production:   We summarize what we learned about the quality characteristics and their role in test automation.


Key takeaways: 

1. Learn about the ISO25010 quality characteristics and their part in software testing
2. Use AI as a partner to brainstorm and create something new
3. Collaborate in a team with diverse roles

API testing is a core part of modern testing and delivery pipelines, yet it is often misunderstood or introduced too late. This session provides a practical introduction to REST API automation using Python, focusing on what to test, how to structure tests, and how API tests fit into a modern testing infrastructure.The workshop starts with a short overview of API testing fundamentals and common use cases. As a practical part, we'll have a hands-on walkthrough where we write REST API tests covering basic CRUD operations. Attendees will work with Python and the Requests library against a real service with well-documented APIs.I will provide a basic test framework, and we will extend it together by adding and improving tests during the session. The workshop requires Python 3.13+ installed and basic familiarity with Python to read and write test code.