1 · puedes empezar
Same Prompt, Different Test Suite
~0,8 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.
Tu lección es en tu idioma: la dirige tu asistente.
- Material: inglés
- Examen: inglés; se hace en el sitio, sin traducir
Cómo funciona
Tu asistente toma el material del curso de nuestro servidor y dirige la lección en tu idioma.
El examen se hace en el sitio, sin asistente. Las preguntas del examen no se traducen: así se ha decidido para todos los cursos.
Recorrido por el curso
· 21 unidadeslínea continua: el camino está abierto · discontinua: cerrado por ahoraVista: mapa · niveles
2 · cerrada
The Model You Picked Costs You Twice
~0,7 h
se abre después de «Same Prompt, Different Test Suite»
3 · cerrada
The Screenshot Your Model Cannot Read
~0,7 h
se abre después de «The Model You Picked Costs You Twice»
4 · cerrada
"Make Me Some Test Cases"
~1,1 h
se abre después de «The Screenshot Your Model Cannot Read»
5 · cerrada
Three Techniques, and Where Each Breaks
~1,1 h
se abre después de «"Make Me Some Test Cases"»
6 · cerrada
Finding the Holes in the Requirement
~1 h
se abre después de «Three Techniques, and Where Each Breaks»
7 · cerrada
From Acceptance Criteria to Test Cases
~1 h
se abre después de «Finding the Holes in the Requirement»
8 · cerrada
Gherkin at Scale
~0,9 h
se abre después de «From Acceptance Criteria to Test Cases»
9 · cerrada
The Regression Suite That Heals Itself
~0,9 h
se abre después de «Gherkin at Scale»
10 · cerrada
Reading a Failed Nightly Run
~0,8 h
se abre después de «The Regression Suite That Heals Itself»
11 · cerrada
Numbers the Partner Will Read
~0,7 h
se abre después de «Reading a Failed Nightly Run»
12 · cerrada
Choose the Technique Before You Write
~0,8 h
se abre después de «Numbers the Partner Will Read»
13 · cerrada
Proving the Output Is Good Enough
~0,9 h
se abre después de «Choose the Technique Before You Write»
14 · cerrada
It Sounded Right and It Was Wrong
~0,9 h
se abre después de «Proving the Output Is Good Enough»
15 · cerrada
Turning the Temperature Down
~0,7 h
se abre después de «It Sounded Right and It Was Wrong»
16 · cerrada
Client Data Does Not Leave the Firm
~1 h
se abre después de «Turning the Temperature Down»
17 · cerrada
Who Signs Off That This Was Legal
~0,9 h
se abre después de «Client Data Does Not Leave the Firm»
18 · cerrada
The Model Has Never Seen Your Test Cases
~1,1 h
se abre después de «Who Signs Off That This Was Legal»
19 · cerrada
The Agent That Filed Forty Bad Defects
~0,8 h
se abre después de «The Model Has Never Seen Your Test Cases»
20 · cerrada
When Prompting Is Not Enough
~0,9 h
se abre después de «The Agent That Filed Forty Bad Defects»
21 · cerrada
Shadow AI in an Audit Firm
~0,9 h
se abre después de «When Prompting Is Not Enough»
final · en el navegador, sin el asistente
Examen
cerrada · inscríbete en el curso
El recorrido en palabras
- Nivel 1 · Same Prompt, Different Test Suite — puedes empezar; ~0,8 h
- Nivel 2 · The Model You Picked Costs You Twice — cerrada; se abre después de «Same Prompt, Different Test Suite»; ~0,7 h
- Nivel 3 · The Screenshot Your Model Cannot Read — cerrada; se abre después de «The Model You Picked Costs You Twice»; ~0,7 h
- Nivel 4 · "Make Me Some Test Cases" — cerrada; se abre después de «The Screenshot Your Model Cannot Read»; ~1,1 h
- Nivel 5 · Three Techniques, and Where Each Breaks — cerrada; se abre después de «"Make Me Some Test Cases"»; ~1,1 h
- Nivel 6 · Finding the Holes in the Requirement — cerrada; se abre después de «Three Techniques, and Where Each Breaks»; ~1 h
- Nivel 7 · From Acceptance Criteria to Test Cases — cerrada; se abre después de «Finding the Holes in the Requirement»; ~1 h
- Nivel 8 · Gherkin at Scale — cerrada; se abre después de «From Acceptance Criteria to Test Cases»; ~0,9 h
- Nivel 9 · The Regression Suite That Heals Itself — cerrada; se abre después de «Gherkin at Scale»; ~0,9 h
- Nivel 10 · Reading a Failed Nightly Run — cerrada; se abre después de «The Regression Suite That Heals Itself»; ~0,8 h
- Nivel 11 · Numbers the Partner Will Read — cerrada; se abre después de «Reading a Failed Nightly Run»; ~0,7 h
- Nivel 12 · Choose the Technique Before You Write — cerrada; se abre después de «Numbers the Partner Will Read»; ~0,8 h
- Nivel 13 · Proving the Output Is Good Enough — cerrada; se abre después de «Choose the Technique Before You Write»; ~0,9 h
- Nivel 14 · It Sounded Right and It Was Wrong — cerrada; se abre después de «Proving the Output Is Good Enough»; ~0,9 h
- Nivel 15 · Turning the Temperature Down — cerrada; se abre después de «It Sounded Right and It Was Wrong»; ~0,7 h
- Nivel 16 · Client Data Does Not Leave the Firm — cerrada; se abre después de «Turning the Temperature Down»; ~1 h
- Nivel 17 · Who Signs Off That This Was Legal — cerrada; se abre después de «Client Data Does Not Leave the Firm»; ~0,9 h
- Nivel 18 · The Model Has Never Seen Your Test Cases — cerrada; se abre después de «Who Signs Off That This Was Legal»; ~1,1 h
- Nivel 19 · The Agent That Filed Forty Bad Defects — cerrada; se abre después de «The Model Has Never Seen Your Test Cases»; ~0,8 h
- Nivel 20 · When Prompting Is Not Enough — cerrada; se abre después de «The Agent That Filed Forty Bad Defects»; ~0,9 h
- Nivel 21 · Shadow AI in an Audit Firm — cerrada; se abre después de «When Prompting Is Not Enough»; ~0,9 h
Programa · 21 unidades
| 1 | Same Prompt, Different Test Suite Explain why an LLM returns different output for identical input | ~0,8 h | puedes empezar |
| 2 | The Model You Picked Costs You Twice Distinguish the foundation, instruction-tuned and reasoning stages of LLM training | ~0,7 h | cerrada |
| 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 | cerrada |
| 4 | "Make Me Some Test Cases" Give examples of the six components of a structured prompt for a test task | ~1,1 h | cerrada |
| 5 | Three Techniques, and Where Each Breaks Differentiate prompt chaining, few-shot prompting and meta prompting | ~1,1 h | cerrada |
| 6 | Finding the Holes in the Requirement Apply generative AI to identify defects in the test basis | ~1 h | cerrada |
| 7 | From Acceptance Criteria to Test Cases Apply generative AI to generate test cases from acceptance criteria | ~1 h | cerrada |
| 8 | Gherkin at Scale Use few-shot prompting to produce output in a fixed house format | ~0,9 h | cerrada |
| 9 | The Regression Suite That Heals Itself Apply few-shot prompting to generate keyword-driven test scripts | ~0,9 h | cerrada |
| 10 | Reading a Failed Nightly Run Apply structured prompts to analyse a regression test report | ~0,8 h | cerrada |
| 11 | Numbers the Partner Will Read Apply generative AI to test monitoring and test control tasks | ~0,7 h | cerrada |
| 12 | Choose the Technique Before You Write Select an appropriate prompting technique for a given context and test task | ~0,8 h | cerrada |
| 13 | Proving the Output Is Good Enough Understand the metrics for evaluating generative AI results on test tasks | ~0,9 h | cerrada |
| 14 | It Sounded Right and It Was Wrong Recall the definitions of hallucination, reasoning error and bias | ~0,9 h | cerrada |
| 15 | Turning the Temperature Down Recall mitigation techniques for non-deterministic LLM behaviour | ~0,7 h | cerrada |
| 16 | Client Data Does Not Leave the Firm Explain the key data privacy and security risks of using generative AI in testing | ~1 h | cerrada |
| 17 | Who Signs Off That This Was Legal Recall the AI regulations, standards and best-practice frameworks relevant to testing | ~0,9 h | cerrada |
| 18 | The Model Has Never Seen Your Test Cases Explain the architectural components of LLM-powered test infrastructure | ~1,1 h | cerrada |
| 19 | The Agent That Filed Forty Bad Defects Explain the role of LLM-powered agents in automating test process tasks | ~0,8 h | cerrada |
| 20 | When Prompting Is Not Enough Explain fine-tuning of language models for test tasks and when it is justified | ~0,9 h | cerrada |
| 21 | Shadow AI in an Audit Firm Recall the risks of shadow AI in an organisation handling client data | ~0,9 h | cerrada |