1 · can start
Same Prompt, Different Test Suite
~0.6 h
Generative AI for Software Testing: A Practitioner's Course
A hands-on course on using large language models across the test process: prompting for test analysis and design, evaluating what the model gives back, containing its risks, and rolling it out in an organisation that handles client data. Built around a professional-services engagement, where confidentiality and documented review are not optional. Assumes working knowledge of test design, test levels and defect management.
Path through the course · 21 units
solid line — the way is open · dashed — closed for nowView: map · steps
2 · closed
The Model You Picked Costs You Twice
~0.6 h
3 · closed
The Screenshot Your Model Cannot Read
~0.6 h
4 · closed
"Make Me Some Test Cases"
~1 h
5 · closed
Three Techniques, and Where Each Breaks
~1 h
6 · closed
Finding the Holes in the Requirement
~0.8 h
7 · closed
From Acceptance Criteria to Test Cases
~0.8 h
8 · closed
Gherkin at Scale
~0.8 h
9 · closed
The Regression Suite That Heals Itself
~0.8 h
10 · closed
Reading a Failed Nightly Run
~0.7 h
11 · closed
Numbers the Partner Will Read
~0.6 h
12 · closed
Choose the Technique Before You Write
~0.7 h
13 · closed
Proving the Output Is Good Enough
~0.8 h
14 · closed
It Sounded Right and It Was Wrong
~0.8 h
15 · closed
Turning the Temperature Down
~0.6 h
16 · closed
Client Data Does Not Leave the Firm
~0.8 h
17 · closed
Who Signs Off That This Was Legal
~0.8 h
18 · closed
The Model Has Never Seen Your Test Cases
~0.9 h
19 · closed
The Agent That Filed Forty Bad Defects
~0.7 h
20 · closed
When Prompting Is Not Enough
~0.8 h
21 · closed
Shadow AI in an Audit Firm
~0.8 h
final
Exam
closed
The path in words
- Stage 1 · Same Prompt, Different Test Suite — can start; ~0.6 h
- Stage 2 · The Model You Picked Costs You Twice — closed; all of the previous needed (u01, 0/1); ~0.6 h
- Stage 3 · The Screenshot Your Model Cannot Read — closed; all of the previous needed (u02, 0/1); ~0.6 h
- Stage 4 · "Make Me Some Test Cases" — closed; all of the previous needed (u03, 0/1); ~1 h
- Stage 5 · Three Techniques, and Where Each Breaks — closed; all of the previous needed (u04, 0/1); ~1 h
- Stage 6 · Finding the Holes in the Requirement — closed; all of the previous needed (u05, 0/1); ~0.8 h
- Stage 7 · From Acceptance Criteria to Test Cases — closed; all of the previous needed (u06, 0/1); ~0.8 h
- Stage 8 · Gherkin at Scale — closed; all of the previous needed (u07, 0/1); ~0.8 h
- Stage 9 · The Regression Suite That Heals Itself — closed; all of the previous needed (u08, 0/1); ~0.8 h
- Stage 10 · Reading a Failed Nightly Run — closed; all of the previous needed (u09, 0/1); ~0.7 h
- Stage 11 · Numbers the Partner Will Read — closed; all of the previous needed (u10, 0/1); ~0.6 h
- Stage 12 · Choose the Technique Before You Write — closed; all of the previous needed (u11, 0/1); ~0.7 h
- Stage 13 · Proving the Output Is Good Enough — closed; all of the previous needed (u12, 0/1); ~0.8 h
- Stage 14 · It Sounded Right and It Was Wrong — closed; all of the previous needed (u13, 0/1); ~0.8 h
- Stage 15 · Turning the Temperature Down — closed; all of the previous needed (u14, 0/1); ~0.6 h
- Stage 16 · Client Data Does Not Leave the Firm — closed; all of the previous needed (u15, 0/1); ~0.8 h
- Stage 17 · Who Signs Off That This Was Legal — closed; all of the previous needed (u16, 0/1); ~0.8 h
- Stage 18 · The Model Has Never Seen Your Test Cases — closed; all of the previous needed (u17, 0/1); ~0.9 h
- Stage 19 · The Agent That Filed Forty Bad Defects — closed; all of the previous needed (u18, 0/1); ~0.7 h
- Stage 20 · When Prompting Is Not Enough — closed; all of the previous needed (u19, 0/1); ~0.8 h
- Stage 21 · Shadow AI in an Audit Firm — closed; all of the previous needed (u20, 0/1); ~0.8 h
Programme · 21 units
| 1 | Same Prompt, Different Test Suite Explain why an LLM returns different output for identical input | ~0.6 h | can start |
| 2 | The Model You Picked Costs You Twice Distinguish foundation, instruction-tuned and reasoning LLMs | ~0.6 h | closed |
| 3 | The Screenshot Your Model Cannot Read Write and execute a prompt combining a wireframe and a user story for a test task | ~0.6 h | closed |
| 4 | "Make Me Some Test Cases" Give examples of the six components of a structured prompt for a test task | ~1 h | closed |
| 5 | Three Techniques, and Where Each Breaks Differentiate prompt chaining, few-shot prompting and meta prompting | ~1 h | closed |
| 6 | Finding the Holes in the Requirement Apply generative AI to identify defects in the test basis | ~0.8 h | closed |
| 7 | From Acceptance Criteria to Test Cases Apply generative AI to generate test cases from acceptance criteria | ~0.8 h | closed |
| 8 | Gherkin at Scale Use few-shot prompting to produce output in a fixed house format | ~0.8 h | closed |
| 9 | The Regression Suite That Heals Itself Apply few-shot prompting to generate keyword-driven test scripts | ~0.8 h | closed |
| 10 | Reading a Failed Nightly Run Apply structured prompts to analyse a regression test report | ~0.7 h | closed |
| 11 | Numbers the Partner Will Read Apply generative AI to test monitoring and test control tasks | ~0.6 h | closed |
| 12 | Choose the Technique Before You Write Select an appropriate prompting technique for a given context and test task | ~0.7 h | closed |
| 13 | Proving the Output Is Good Enough Understand the metrics for evaluating generative AI results on test tasks | ~0.8 h | closed |
| 14 | It Sounded Right and It Was Wrong Recall the definitions of hallucination, reasoning error and bias | ~0.8 h | closed |
| 15 | Turning the Temperature Down Recall mitigation techniques for non-deterministic LLM behaviour | ~0.6 h | closed |
| 16 | Client Data Does Not Leave the Firm Explain the key data privacy and security risks of using generative AI in testing | ~0.8 h | closed |
| 17 | Who Signs Off That This Was Legal Recall the AI regulations, standards and best-practice frameworks relevant to testing | ~0.8 h | closed |
| 18 | The Model Has Never Seen Your Test Cases Explain the architectural components of LLM-powered test infrastructure | ~0.9 h | closed |
| 19 | The Agent That Filed Forty Bad Defects Explain the role of LLM-powered agents in automating test process tasks | ~0.7 h | closed |
| 20 | When Prompting Is Not Enough Explain fine-tuning of language models for test tasks and when it is justified | ~0.8 h | closed |
| 21 | Shadow AI in an Audit Firm Recall the risks of shadow AI in an organisation handling client data | ~0.8 h | closed |