LSI

Module Specification

Advanced AI Prompt Engineering

Module Specification

Advanced AI Prompt Engineering: Master the Art of AI Communication


Large language models, such as ChatGPT, have transformed how we interact with technology. Leveraging their full capabilities, however, requires more than basic queries.

This module delves into the art and science of crafting prompts that elicit precise and relevant responses from GenAI systems. You will explore the principles of prompt design and learn how different types of prompts influence AI behaviour.

The module covers advanced techniques such as chain-of-thought prompting, zero-shot and few-shot learning, and context-aware prompting. It also includes instruction tuning, multi-modal prompting, dynamic prompting, and adjusting model parameters to control AI response characteristics.

By mastering these skills, you will harness GenAI effectively in real-world scenarios across various industries, from healthcare and finance, and retail and entertainment. You will develop the expertise to create AI solutions that are accurate, relevant, and ethically responsible.

Equip yourself with confidence and authority to navigate and shape the evolving landscape of AI-driven interactions.



Prerequisites and Co-requisites

None

Learning Outcomes

Code Attributes developed Outcomes
LO1 Knowledge and Understanding Describe key prompt engineering principles and how prompt structure, context, and iteration influence AI outputs.
LO2 Knowledge and Understanding Explain the core components of generative AI systems, including large language models.
LO3 Intellectual Skills Apply ethical reasoning to prompt design, taking into account issues such as bias and the responsible use of AI-generated content.
LO4 Technical/Practical Skills Construct and refine prompts using advanced techniques to guide AI systems towards accurate, relevant, and context-aware outputs.
LO5 Technical/Practical Skills Experiment with dynamic prompting strategies and make informed adjustments to improve AI outputs.
LO6 Professional/Transferable Skills Communicate effectively with AI systems as collaborative thinking partners, leveraging prompt engineering for creative, analytical, and problem-solving tasks across professional domains.

Content Structure

Week Topic
Week 1 Introductory lecture
Introduces the module, outlining its relevance to the field and connections to other topics. It provides an overview of the content structure, key references, and assessment details.
Week 2 Understanding Generative AI
Build a solid foundation in generative AI and large language models to appreciate how AI interprets and generates human-like text. Understand why effective communication with AI is crucial to unlocking its full potential. Grasping these concepts helps you harness AI capabilities more effectively.
Week 3 Prompt Engineering Foundations
Learn to design prompts that consistently generate accurate and relevant AI responses. Master the art of balancing precision and flexibility in prompts to achieve optimal results. Understanding these principles empowers you to communicate your intentions clearly to the AI.
Week 4 Advanced Prompt Techniques
Explore advanced techniques like chain-of-thought prompting, zero-shot and few-shot learning. Delve into why these methods enhance AI's problem-solving abilities and enable it to perform tasks without extensive examples. Using these strategies, you can tackle complex tasks more effectively.
Week 5 Professional Prompting Acumen
Learn practical guidelines and best practices for balancing commercial benefits and security considerations to enable successful and responsible AI adoption in business settings.
Week 6 Dynamic Prompting and Integration
Harness the power of context-aware and dynamic prompting. Discover why embedding context within prompts enhances relevance and accuracy. Learn to modify prompts in real time based on AI responses to maintain effective communication.

Student Workload

The methods of teaching and learning for this module are based on the School's Short-course 5 teaching system, consisting of the following activities.

Activity
Introductory lecture
Concept learning (knowledge graph)
AI formative assessment
Case Study Review
Independent reading, exploration and practice
Total:

Teaching and Learning Methods

Activity Description
Introductory lecture

This is the first weekly session, dedicated to providing a comprehensive introduction to the module. The module leader will present an overview of the subject, elucidating its importance within various digital engineering professions and its interrelation with other modules. Students will need no preparation ahead of attending this session.

The module leader will provide a structured breakdown of the content to be covered in the subsequent 9 sessions. Students will also receive an outline of the essential reference materials, alongside suggestions for supplementary reading. The format and criteria for the summative assessment will be delineated, followed by a dedicated period for questions and answers.

A recording of the session will be available to facilitate async engagement for any other student who missed the class, also offering an opportunity to review the content again.
Concept learning (knowledge graph)

Our institution's approach to teaching is primarily based on flipped learning. Ahead of each weekly session (Workshop/Lab), students will be required to study the essential concepts that are used in the coming session so they are familiar with the theories and ideas related to that session. The study material will be in the form of written content, illustrations, pre-recorded lectures and tutorials, and other forms of content provided through the AGS.

This content is self-navigated by the students, accommodating different learning styles and schedules, allowing students to watch or listen to them at their own pace and review them as needed.
AI formative assessment

Once each concept of the theory is studied, students will be prompted to engage in formative assessment with instant AI feedback. They include multiple-choice questions, socratic questions and answers, written questions, role-play and other AI-assisted practice scenarios.

The purpose of this automated formative assessment is to provide students with immediate feedback on their understanding of module material and highlight any areas that need support or further study. They are also used to track student progress, boost motivation and promote accountability.
Case Study Review

In this learning activity, students explore recent real-world case studies relevant to their course topic. The case studies will have been selected and curated by the module leader to represent up-to-date examples. They guide students through key details, contextual factors, and outcomes. This approach enhances students' understanding of current industry trends, challenges, and solutions, preparing them for real-world scenarios they may encounter in their future careers.

The learning experienced will be augmented by AI (virtual private tutor) allowing the students to critically engage with the content and discuss the case studies.
Independent reading, exploration and practice

This activity challenges students to engage with the reference material and independently explore and analyse academic literature related to the course topic. Students are expected to select relevant sources, practice critical reading skills, and where applicable technical skills, and synthesise information from multiple references. This is an opportunity to enhance research abilities, critical thinking, and self-directed learning skills while broadening and deepening subject knowledge.

Module Approval

Stage Version Date of approval Authority Chair Revalidation
Compliance 1.0 Academic Board Dr Paresh Kathrani
Pre-Teaching 1.0 Director of Education Dr Paresh Kathrani
Note: The information detailed within this record is accurate at the time of publishing and may be subject to change.
Module Spec: Advanced AI Prompt Engineering: Master the Art of AI Communication (PE01)