Section outline

  • Collapse Expand

    Welcome!

    Collapse all Expand all

            

    Welcome to the demo for AI for Testers! In this course, you’ll learn practical ways to use AI in your testing work and evaluate the quality and risks of systems that contain AI. Through examples and exercises, you’ll build on your testing skills while strengthening the human judgment that effective testing still requires. My goal was to create a short, practical course for software testers who want to learn how to apply AI in their daily work, without feeling like you're becoming an AI engineer or data scientist. I hope I have met that goal!

    In this demo, you will notice that many of the links are disabled due to the nature of the demo. I have left the topics in place to show the outline of the course. To purchase an enrollment, just visit https://mysoftwaretesting.com/AI-For-Testers_p_150.html

  • Collapse Expand

    Module 1 — Understanding What You’re Testing

      

    • Slides in PDF File
    • Lesson 1 - AI Without the Hype (22:09) URL

    • Exercise

      In this exercise, we will use Google Gemini to generate some test cases from a short requirement.
      The requirement:
      The system shall be able to calculate postage based on weight:
      Under 1 pound, the postage is $10
      From 1 pound to 4.99 pounds, the postage is $15
      From 5 pounds to 9.99 pounds, the postage is $20
      Over 10 pounds, the postage is $2.95 per pound

      Instructions
      Go to google.com and click on AI Mode.
      Enter the following prompt. (Note the key elements of the prompt)
      Context – I am a tester working on creating test cases to verify a requirement for calculating postage rates.
      Instruction – Create test cases that contain specific conditions and expected results for the following requirement.
      Data – [Insert requirement here]
      Format – The test case must show test conditions and expected results
      Constraints – Limit the number of test cases to the minimal amount needed to verify the requirement.

      Verify the output. Did it match your expectations?

    • Exercise Solution (7:17) URL
    • Lesson 2 - How AI Systems Are Different (6:14) URL
    • Lesson 3 - Where AI Failures Come From (5:16) URL
    • Lesson 4 - Training, Validation, Testing—and Production (18:54) URL
    • Lesson 5 - The AI System, Not Just the Model (8:43) URL
  • Collapse Expand

    Module 2 — Testing AI Systems

            

  • Collapse Expand

    Module 3 — Using AI as a Testing Tool

          

    • Reusable Prompt Library File
    • Lesson 1 - AI as a Testing Assistant—Not an Oracle (9:54) URL
    • Lesson 2 - Using AI to Generate Test Ideas (13:32) URL

    • Exercise

      You have a simple requirement:
      “A user account will be locked after three unsuccessful login attempts.”

      Write down about five test ideas individually, without using AI.
      Then use AI.
      Ask it to identify ambiguities, risks, boundaries, and test ideas.

    • Exercise Solution (7:09) URL
    • Lesson 3 - Using AI to Analyze Requirements (10:00) URL

    • Exercise

      Consider this requirement: “Users can reset a forgotten password by entering their email address. A reset link will be sent to the user and will expire after 30 minutes.”
      Do you see any problems with this requirement?
      Now, use AI to examine this requirement.

    • Exercise Solution (4:36) URL
    • Lesson 4 - Using AI to Improve Test Assets (16:39) URL

    • Exercise

      Consider this requirement: Customers may return most items within 30 days of purchase with a receipt for a full refund.
      Consider the associated test case:

      Preconditions: Customer has purchased an item
      Test Data: Item, receipt
      Steps: 1. Log in. 2. Select the item. 3. Choose Return. 4. Complete the return process.
      Expected Result: The return should work correctly.

      Prompt: Critique this requirement and test case. Identify weaknesses, assumptions, missing coverage, and anything that would make the test difficult to execute or evaluate. Do not invent requirements that aren't stated.

    • Exercise Solution (13:20) URL
    • Lesson 5 - Testing AI-Generated Code and Tests (17:23) URL
  • Collapse Expand

    Module 4 — Building a Responsible AI Testing Strategy

      

    • AI Test Evaluation Record File
    • Lesson 1 - Risk-Based Testing for AI (13:57) URL

    • Exercise

      Consider 3 AI systems:
      A. AI recommends movies to streaming customers.
      B. AI determines whether insurance claims should be flagged for investigation.
      C. AI assistant helps technicians diagnose problems with industrial equipment.

      Identify the top three failures you would worry about for each.

      Then determine:
      Impact → Likelihood/uncertainty → Exposure → Testing response

    • Exercise Solution (4:41) URL
    • Lesson 2 - Evaluating AI Quality (14:42) URL
    • Lesson 3 - Evaluating AI Quality (16:49) URL

    • Exercise

      ShopSmart is an online retailer selling clothing, electronics, and household products.
      The company is introducing an AI-powered customer service assistant to reduce the workload of its support staff.
      The assistant will:

      • Answer questions about products, shipping, and returns.
      • Retrieve information from ShopSmart's product catalog and return policies.
      • Look up customer order status after verifying the customer's identity.
      • Recommend products based on customer preferences.
      • Refer customers to a human representative when it cannot resolve an issue.

      The assistant uses a large language model (LLM) and retrieval-augmented generation (RAG) to access company information.

      Important Business Rules

      • Most products can be returned within 30 days.
      • Electronics must be returned within 15 days.
      • The assistant cannot approve exceptions or issue refunds.
      • Customer information must not be disclosed to unauthorized users.
      • The assistant must not invent product specifications or company policies.

      ShopSmart plans to launch the assistant in four weeks.

      Develop a basic AI test strategy for ShopSmart.

      Address these six areas:
      1. Key Risks - Identify the three most important risks associated with the assistant.
      2. Quality Characteristics - Which AI quality characteristics matter most?
      3. Acceptance Criteria - How will you determine whether the assistant performs acceptably?
      4. Test Approach - What types of testing will you perform?
      5. Test Data - What scenarios and data will you need?
      6. Monitoring - What should ShopSmart monitor after deployment?

    • Exercise Solution (3:28) URL
    • Lesson 4 - Governance and Controls Testers Should Understand (11:49) URL
    • Lesson 5 - The Tester in an AI World (10:58) URL
    • AI Test Strategy Template File
  • Collapse Expand

    Summary