Missions & Challenges

Answer Tarek Roshdy’s question for a chance to receive a ShiftSync giftbox.  Only in Death does Duty End

 Take on the challenge for a chance to win! The lucky winner will walk away with a gift box from ShiftSync!🎁👉 An AI agent is asked to test the Login flow on a neobank app.It finds the username field, enters credentials, but then the OTP screen appears unexpectedly.What should a well-designed agentic test do?Drop your answers in the comments. 🕒 Submissions: Submit within one week after the conference ends.

👉Everything you will need for the Solo task is on the GitHub hereClone a real GitHub repo Write a SKILLS definition using a provided template Generate meaningful, context-aware test cases you can talk about in interviews Submit your results in the comments of this thread (e.g., in the form of links and screenshots).🕒 Submissions: If time runs short during the meetup, participants will have up to 24 hours after the event to submit their solo task. 🏆 Winner: Best Solo Submission will get a gift from us 

Answer Nikolay Advolodkin’s question for a chance to receive a ShiftSync giftbox.  

GROUP ACTIVITY: Testing Agents Orchestration1. Create Playwright Testing Agent2. Create Backend Testing Agent3. Create BDD Testing AgentOrchestrate all these agents to work together in a coordinated manner to achieve comprehensive testing coverage for the application. GROUP ACTIVITY: Testing Agents Orchestration with SKILLS1. Create Playwright Testing Agent with SKILLS2. Create Backend Testing Agent with SKILLS3. Create BDD Testing Agent with SKILLS

... Because I have, a couple of times. The most chaotic one was while working on a national health application in the UK, where my refactor to the API which made the application more testable meant that patients nationwide couldn't access information about their prescriptions for a couple of hours during the day. The panic set in realising that my changes had gone through to production too soon... Revert revert!!!I would rate that a 7 out of 10... Do you agree? Anyone got a more severe bug than that?Share your failure story in the comments, and I will pick three winners who will get the book “Contract Testing in Action. With Pact, PactFlow, and GitHub Actions” from ShiftSync.The challenge closes in 10 days.  

Take on Maryia’s challenge for a chance to win! The lucky winner will walk away with a gift box from us!🎁Go to https://gandalf.lakera.ai/baseline and try the Gandalf prompt injection challenge. Share your results in the thread below. Which level did you manage to reach? Please attach screenshots. Share your main insight from doing this exercise. You have 24 hours after the end of the webinar to complete the task!

Take on Naveen’s challenge for a chance to win! The lucky winner will walk away with a gift box from us!🎁You have 24 hours following the webinar to submit your solution.Difficulty: AdvancedTime: 60-90 minutesCreate a complete 4-step AI risk framework (Identify, Assess, Mitigate, Monitor) customized for your project.What to Do:• Document your project's context: tech stack, team size, sprint length, deployment frequency, main modules.• For each of the 4 steps, create: - IDENTIFY: 3 reusable AI prompts your team can use during sprint planning to analyze new stories/requirements. - ASSESS: A risk scoring template (spreadsheet or document) that your team fills with data each sprint, then feeds to AI for scoring. - MITIGATE: A test prioritization prompt template that takes your risk scores + test suite data and outputs a test plan. - MONITOR: A checklist of what to watch post-release and how AI can help detect anomalies.• Write a 1-page "Quick Start Guide" that any team member can follow to

Take on Filip’s challenge for a chance to win! The lucky winner will walk away with a gift box from us!🎁What are the three biggest challenges for quality in the AI era?Drop your answers in the comments below. 

👽Answer Rahul’s question for a chance to receive a ShiftSync giftbox.If you are doing this activity, you have already attended the webinar session. Good. Now show that you can apply the learnings.The TaskPick one real testing problem from your current work.Not a sci-fi ambition. Not “AI will replace QA.” A real, recurring, frustrating task.Now design a lightweight AI Agent Use Case for it using the 5W1H framework:What will the agent do? Why should this be an agent? (Business value + Practitioner value) When – What agency level will it operate at? (Rule-based, Workflow, Semi-autonomous, Autonomous) Where will it fit in your SDLC  / STLC? Who controls or reviews it? How will it roughly work? (LLM? APIs? Tools? Deterministic logic? Memory?)Bonus pointsGive your agent a name Define failure modes and how will you guard against them. If you attach a small prototype, demo, GitHub link, agent snippet, or architecture sketch, you will get extra bonus points. Even a rough proof-of-concept count

Solo Activity (20 min) In 20 minutes, you’ll have to take a basic AI response (SLOP) and improve it toward higher quality, following the SLOP → KINO continuum.You’ll have to use one of the core ShiftSync features to submit and reflect.Here is the step by step demonstration of the activity.1️⃣ Pick ONE ShiftSync featureChoose any one to focus on:Search Feature (Available on Home page) Create Topic Feature Community Zone Feature My Profile Feature (Home > My profile) User Profile → Settings Feature  2️⃣ Craft an Initial PromptUse an AI tool (ChatGPT, Claude, Gemini, Copilot etc.) to generate output related to your chosen feature.Choose any one goal to work on:Test cases / edge cases Diverse use cases / user journeys Test ideas A mini help article  NOTE: Record your original prompt. 3️⃣ Analyze the AI Output Critically review the AI result and identify at least 3 specific weaknesses, gaps, wrong assumptions, or missing edge cases.Note: Be specific and state what’s wrong and why it matt

Group Activity (35 min)This is a team-based activity where groups use AI + human insight to craft a test strategy for a real feature/scenario. You have to collaborate, critique AI output, and produce a stronger end result together.Objective: Build a test strategy that combines AI speed with human critical insight.Time: 35 minutesSubmission: One post per team in this thread 1️⃣ Setup a TeamAssign a group leader. Assign a group name. Write down the names of all members in your group 2️⃣ Understand Activity MissionProduce a test strategy for ShiftSync that covers testing across the key platform features you explored earlier.Core features to include as test strategy areas:Search Feature Create Topic Feature Community Zone My Profile User Profile → Settings Note: Treat these features as the core part of your test strategy. 3️⃣ Use AI to Produce a Baseline StrategyCollaboratively craft a prompt to ask your AI tool for a comprehensive test strategy covering all the core features above.Example

Answer Nikolay Advolodkin’s question for a chance to receive a ShiftSync giftbox.  

Where are you in your adoption of AI in your QE practice?  Just starting?  Pilot running?  Seeing ROI, if so, what does that look like for you?  

Answer Ajay's question and take a shot at winning a gift box.  

Answer Karthik's question and take a shot at winning a gift box.