1 · disponible
Same Prompt, Different Test Suite
~0,8 h

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.
Votre leçon est dans votre langue : c’est votre assistant qui la mène.
Votre assistant récupère le contenu du cours sur notre serveur et mène la leçon dans votre langue.
L’examen se passe sur le site, sans assistant. Les questions d’examen ne sont pas traduites : c’est la règle pour tous les cours.
trait plein — le chemin est ouvert · pointillés — fermé pour l’instantAffichage: carte · niveaux
1 · disponible
Same Prompt, Different Test Suite
~0,8 h
2 · fermée
The Model You Picked Costs You Twice
~0,7 h
s’ouvre après « Same Prompt, Different Test Suite »
3 · fermée
The Screenshot Your Model Cannot Read
~0,7 h
s’ouvre après « The Model You Picked Costs You Twice »
4 · fermée
"Make Me Some Test Cases"
~1,1 h
s’ouvre après « The Screenshot Your Model Cannot Read »
5 · fermée
Three Techniques, and Where Each Breaks
~1,1 h
s’ouvre après « "Make Me Some Test Cases" »
6 · fermée
Finding the Holes in the Requirement
~1 h
s’ouvre après « Three Techniques, and Where Each Breaks »
7 · fermée
From Acceptance Criteria to Test Cases
~1 h
s’ouvre après « Finding the Holes in the Requirement »
8 · fermée
Gherkin at Scale
~0,9 h
s’ouvre après « From Acceptance Criteria to Test Cases »
9 · fermée
The Regression Suite That Heals Itself
~0,9 h
s’ouvre après « Gherkin at Scale »
10 · fermée
Reading a Failed Nightly Run
~0,8 h
s’ouvre après « The Regression Suite That Heals Itself »
11 · fermée
Numbers the Partner Will Read
~0,7 h
s’ouvre après « Reading a Failed Nightly Run »
12 · fermée
Choose the Technique Before You Write
~0,8 h
s’ouvre après « Numbers the Partner Will Read »
13 · fermée
Proving the Output Is Good Enough
~0,9 h
s’ouvre après « Choose the Technique Before You Write »
14 · fermée
It Sounded Right and It Was Wrong
~0,9 h
s’ouvre après « Proving the Output Is Good Enough »
15 · fermée
Turning the Temperature Down
~0,7 h
s’ouvre après « It Sounded Right and It Was Wrong »
16 · fermée
Client Data Does Not Leave the Firm
~1 h
s’ouvre après « Turning the Temperature Down »
17 · fermée
Who Signs Off That This Was Legal
~0,9 h
s’ouvre après « Client Data Does Not Leave the Firm »
18 · fermée
The Model Has Never Seen Your Test Cases
~1,1 h
s’ouvre après « Who Signs Off That This Was Legal »
19 · fermée
The Agent That Filed Forty Bad Defects
~0,8 h
s’ouvre après « The Model Has Never Seen Your Test Cases »
20 · fermée
When Prompting Is Not Enough
~0,9 h
s’ouvre après « The Agent That Filed Forty Bad Defects »
21 · fermée
Shadow AI in an Audit Firm
~0,9 h
s’ouvre après « When Prompting Is Not Enough »
final · dans le navigateur, sans l’assistant
Examen
fermée · inscrivez-vous au cours
| 1 | Same Prompt, Different Test Suite Explain why an LLM returns different output for identical input | ~0,8 h | disponible |
| 2 | The Model You Picked Costs You Twice Distinguish the foundation, instruction-tuned and reasoning stages of LLM training | ~0,7 h | fermée |
| 3 | The Screenshot Your Model Cannot Read Write and execute a prompt combining a wireframe and a user story for a test task | ~0,7 h | fermée |
| 4 | "Make Me Some Test Cases" Give examples of the six components of a structured prompt for a test task | ~1,1 h | fermée |
| 5 | Three Techniques, and Where Each Breaks Differentiate prompt chaining, few-shot prompting and meta prompting | ~1,1 h | fermée |
| 6 | Finding the Holes in the Requirement Apply generative AI to identify defects in the test basis | ~1 h | fermée |
| 7 | From Acceptance Criteria to Test Cases Apply generative AI to generate test cases from acceptance criteria | ~1 h | fermée |
| 8 | Gherkin at Scale Use few-shot prompting to produce output in a fixed house format | ~0,9 h | fermée |
| 9 | The Regression Suite That Heals Itself Apply few-shot prompting to generate keyword-driven test scripts | ~0,9 h | fermée |
| 10 | Reading a Failed Nightly Run Apply structured prompts to analyse a regression test report | ~0,8 h | fermée |
| 11 | Numbers the Partner Will Read Apply generative AI to test monitoring and test control tasks | ~0,7 h | fermée |
| 12 | Choose the Technique Before You Write Select an appropriate prompting technique for a given context and test task | ~0,8 h | fermée |
| 13 | Proving the Output Is Good Enough Understand the metrics for evaluating generative AI results on test tasks | ~0,9 h | fermée |
| 14 | It Sounded Right and It Was Wrong Recall the definitions of hallucination, reasoning error and bias | ~0,9 h | fermée |
| 15 | Turning the Temperature Down Recall mitigation techniques for non-deterministic LLM behaviour | ~0,7 h | fermée |
| 16 | Client Data Does Not Leave the Firm Explain the key data privacy and security risks of using generative AI in testing | ~1 h | fermée |
| 17 | Who Signs Off That This Was Legal Recall the AI regulations, standards and best-practice frameworks relevant to testing | ~0,9 h | fermée |
| 18 | The Model Has Never Seen Your Test Cases Explain the architectural components of LLM-powered test infrastructure | ~1,1 h | fermée |
| 19 | The Agent That Filed Forty Bad Defects Explain the role of LLM-powered agents in automating test process tasks | ~0,8 h | fermée |
| 20 | When Prompting Is Not Enough Explain fine-tuning of language models for test tasks and when it is justified | ~0,9 h | fermée |
| 21 | Shadow AI in an Audit Firm Recall the risks of shadow AI in an organisation handling client data | ~0,9 h | fermée |