Loading demo links...
What to study for each AI4RE domain
AI Basics
Covers core artificial intelligence concepts relevant to requirements engineering, including machine learning, supervised and unsupervised learning, and natural language processing. It also addresses training data, overfitting, inference, and why AI output remains probabilistic and needs human review.
Key skills
machine learning basics, supervised and unsupervised learning, NLP, generative AI, training data quality, overfitting, inference
Large Language Models (LLMs)
Explains how large language models generate text by predicting likely continuations, and covers tokens, context windows, and settings such as temperature. It also addresses key limits including hallucination, knowledge cutoff, and grounding answers in retrieved documents.
Key skills
next-token prediction, tokens, context window, hallucination, temperature, fine-tuning vs prompting, embeddings, retrieval-augmented generation
Prompt Engineering
Covers writing clear prompts with relevant context, scope constraints, and a specified output format for elicitation and analysis tasks. It also includes zero-shot and few-shot examples, role prompting, step-by-step analysis, and iterative refinement and evaluation of outputs.
Key skills
clear instructions, context and constraints, output formats, few-shot prompting, role prompting, step-by-step analysis, iterative refinement
Risks and Responsibilities in AI4RE
Addresses bias, privacy, confidentiality, and fairness risks when AI tools process stakeholder and project information. It also covers accountability, transparency, traceability, and the human verification duties that apply before AI-drafted requirements are baselined.
Key skills
bias and fairness, privacy and anonymisation, confidentiality, accountability, transparency, automation bias, verification before baselining
Use Cases for AI in Requirements Engineering
Presents concrete applications of AI across the requirements engineering lifecycle, from summarising interviews and drafting user stories to detecting ambiguity, duplicates, and conflicts. It also covers feedback clustering, glossary building, completeness checks, and deriving acceptance criteria and test ideas.
Key skills
interview summarisation, user story drafting, ambiguity detection, duplicate and conflict detection, feedback clustering, acceptance criteria drafting, completeness checks