Generative AI and Prompt Engineering Foundations

Learn the foundations of generative AI and large language models (LLMs)

Generative AI is transforming how organisations create, analyse, and work with information. On this three-week course, you’ll explore the technology behind modern generative AI and develop practical skills for working with large language models (LLMs).

You’ll discover how generative AI differs from traditional machine learning, explore the transformer architecture behind today’s LLMs, and learn how models such as GPT are trained. You’ll also compare proprietary and open-source LLMs while considering important responsible AI issues, including bias, safety, and misuse.

Develop practical prompt engineering skills

Effective prompts are essential for getting reliable results from generative AI. You’ll learn how to structure and refine prompts, applying zero-shot, one-shot, and few-shot prompting techniques to tasks.

Through iterative testing and debugging, you’ll develop the ability to identify weak prompts and improve their performance. You’ll then explore advanced prompt engineering techniques, including chain-of-thought, tree-of-thought, self-consistency, and generated-knowledge prompting.

Apply generative AI responsibly and securely

As generative AI becomes increasingly important in the workplace, understanding its risks is just as important as knowing how to use it. You’ll explore adversarial prompting and prompt injection, learning how these techniques can compromise LLM applications and how to defend against them.

You’ll also discover how human-in-the-loop refinement can improve AI outputs, helping you develop a more reliable and responsible approach to working with generative AI.

By the end of the course, you’ll understand how LLMs work and have the prompt engineering expertise to apply generative AI effectively.

This introductory course is designed for software developers, data analysts, machine learning practitioners, and technical professionals who can already program in Python and understand basic machine learning concepts, and who now want to build practical generative AI skills.

No prior experience with large language models or prompt engineering is required. It is ideal for developers moving into AI product work, data professionals adding GenAI capability to their role, and engineers preparing for prompt engineer or junior LLM developer positions. Learners should be comfortable writing Python and reading code before starting. By the end, they will understand how LLMs work and be able to design reliable prompts for real tasks.

This introductory course is designed for software developers, data analysts, machine learning practitioners, and technical professionals who can already program in Python and understand basic machine learning concepts, and who now want to build practical generative AI skills.

No prior experience with large language models or prompt engineering is required. It is ideal for developers moving into AI product work, data professionals adding GenAI capability to their role, and engineers preparing for prompt engineer or junior LLM developer positions. Learners should be comfortable writing Python and reading code before starting. By the end, they will understand how LLMs work and be able to design reliable prompts for real tasks.

• Explain the fundamentals of generative AI, large language models, transformers, tokenisation, attention, and the LLM training lifecycle.
• Compare proprietary and open-source LLMs based on their capabilities, use cases, and responsible AI considerations.
• Apply zero-shot, one-shot, and few-shot prompting to question answering, summarisation, classification, and other language tasks.
• Evaluate prompt injection risks and apply defensive and human-in-the-loop techniques to improve LLM safety.
• Develop an end-to-end prompted application that combines effective prompting, reasoning, safety, and context-management techniques.
• Design context-engineering workflows using retrieved knowledge, conversation memory, context ordering, and token-budget management.