| Mode(s) of Study | Code | CATS Credits | ECTSCredits | Framework | HECoSCode |
|---|---|---|---|---|---|
| Flexible online | LL71O | 30 | 15 | FHEQ - L7 | artificial intelligence |
Prerequisites and Co-requisites
Learning Outcomes
| Code | AttributesDeveloped | Outcomes |
|---|---|---|
| LO1 | Knowledge and Understanding | Demonstrate comprehensive knowledge of advanced LLM customisation techniques and integration in multi-step interaction workflows. |
| LO2 | Intellectual Skills | Analyse ethical implications and data privacy challenges in human-LLM collaboration and workflow integration. |
| LO3 | Intellectual Skills | Critically evaluate methodologies for managing conversation states and task decomposition in complex multi-turn LLM interactions. |
| LO4 | Technical/Practical Skills | Develop custom LLM agents utilising frameworks like LangChain to autonomously manage tasks with human oversight inclusions. |
| LO5 | Technical/Practical Skills | Implement secure database integrations with LLMs, ensuring data security and privacy through advanced anonymisation techniques. |
Student Workload
The methods of teaching and learning for this module are based on LSI's Technical 30 teaching system, consisting of the following activities.
| Activity | TotalHours |
|---|---|
| Introductory lecture | 1.50 |
| Concept learning (knowledge graph) | 36.00 |
| AI formative assessment | 18.00 |
| Workshop/Lab Sessions | 27.00 |
| Independent reading, exploration and practice | 153.50 |
| Summative assessment | 64.00 |
| Total: | 300.00 |
Teaching and Learning Methods
| Activity | Description |
|---|---|
| Introductory lecture | This first weekly session features a specially recorded video by the module leader for online learners, providing a comprehensive introduction to the module. The video outlines the significance of the subject and its interrelation with other modules. No preparation is required from students prior to this session. The module leader will also provide a structured breakdown of the content to be covered in the subsequent 10 sessions. Students will access a dedicated learning portal, which will include essential reference materials and suggestions for supplementary reading. The format and criteria for the summative assessment will be clearly outlined to ensure understanding of expectations. The video will also explain how the interactive learning platform utilises generative AI tools to enhance the learning experience, offering tailored resources and adaptive quizzes. A discussion board will promote peer interaction, allowing students to share insights and ask questions, while weekly reflection prompts will encourage critical thinking and deeper engagement with the material. A dedicated section for submitting queries will ensure timely responses from the module leader. This structured approach promotes a high-quality academic experience, supporting student engagement and learning in an online environment. |
| 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. |
| Workshop/Lab Sessions | For those studying in the self-paced online mode, live classes will be replaced by a set of flexible, self-directed activities designed to be completed independently. These include AI-led simulations, interactive videos, reflective prompts, and real-world case studies, all aimed at deepening understanding and fostering critical, independent thinking. AI avatars will simulate a classroom environment, allowing students to interact with virtual instructors for guidance or discussion, creating a more immersive experience. This structure promotes a high-quality, autonomous learning experience, equipping students with skills essential for both academic and professional success. Additionally, a dedicated feature for submitting questions to the module leader will provide timely responses and support. |
| 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. |
| Summative assessment | Summative assessments are used to evaluate student learning at the end of a module. These assessments can take many forms, including exams, papers, or presentations. Instructors can use summative assessments to measure whether students have achieved the learning outcomes for the module and provide them with a sense of their overall progress. Summative assessments can also be used to evaluate the effectiveness of the teaching methods used in the module. |
Assessment Patterns
| Weighting | Format | Outcomes assessed |
|---|---|---|
| 40 |
Invigilated Exam
This is a time-limited examination undertaken during the summative assessment period under the School’s remote invigilation conditions to support quality and academic integrity. The examination enables students to demonstrate achievement of the module learning outcomes, particularly in relation to knowledge and understanding, and where relevant professional and transferable skills. Questions may include problems, issues or dilemmas reflecting situations students could encounter in professional practice. Students are expected to synthesise and apply their learning to analyse the issues and reach sound, reasoned judgements. To support preparation, formative assessment activities, including quizzes, dialogues and an AI-augmented assignment, are built into the module. Students receive actionable feedback from AI, staff and peers to help improve future work and develop their ability to give constructive feedback to others. |
I LO2 I LO3 K LO1 |
| 60 |
Technical Analysis and Solution Assessment Coursework
This coursework assessment requires students to develop a solution to a complex problem in a simulated context, then analyse and reflect on the solution, the decisions they made, and the theory underpinning their approach. It assesses students’ ability to develop practical solutions, critically evaluate their work, and demonstrate their understanding of the module’s technical and theoretical concepts. |
I LO2 I LO3 K LO1 T LO4 T LO5 |
References/Indicative Reading List
| Importance | ISBN | Description |
|---|---|---|
| Core Textbook | 9781040134306 | Atkinson-Abutridy, J. Large Language Models: Concepts, Techniques and Applications. CRC Press, 2024 |
| Core Textbook | 9781501520600 | Campesato, Oswald. Large Language Models: An Introduction. Mercury Learning and Information, 2024 |
| Supplementary Reading | 9781803247335 | Rothman, Denis. Transformers for Natural Language Processing: Build, train, and fine-tune deep neural network architectures for NLP with Python, PyTorch, TensorFlow, BERT, and GPT-3. Packt Publishing, 2022 |
| Supplementary Reading | Biswas, A. and Talukdar, W. (2025) Building Agentic AI Systems: Create Intelligent, Autonomous AI Agents That Can Reason, Plan, and Adapt. Birmingham: Packt Publishing. | |
| Supplementary Reading | Use the LangGraph Graph API to define nodes, edges, state and execution paths within agent workflows. Build structured graphs in Python, connect individual processing steps and practise controlling how information moves through multi-step AI applications. | |
| Supplementary Reading | 9789355519658 | Khandare, SS. Mastering Large Language Models. BPB Publications, 2024. |
| Supplementary Reading | 9781040052174 | Thakurm K. Barker, H. Khan Pathan, A. Artificial Intelligence and Large Language Models: An Introduction to the Technological Future. Chapman and Hall/CRC, 2024 |
| Supplementary Reading | 9789027259158 | Nolan, Brian and Periñán-Pascual, Carlos. Language Processing and Grammars: The role of functionally oriented computational models. John Benjamins Publishing Company, 2014 |
| Supplementary Reading | Use Hugging Face Datasets to find, load and work with datasets for machine learning tasks. Bring structured data into Python workflows, inspect dataset features and practise preparing information for model development, experimentation and evaluation activities. | |
| Supplementary Reading | Use JupyterLab installation guidance to set up an interactive coding workspace on your computer. Create notebooks combining code, notes and outputs, run Python step by step, inspect results and organise practical experiments as you learn. | |
| Supplementary Reading | 9798868800177 | Amaratunga, T. Understanding Large Language Models: Learning Their Underlying Concepts and Technologies. Apress, 2023 |
| Supplementary Reading | 9780138199197 | Ozdemir, Sinan. Quick start guide to large language models: strategies and best practices for using ChatGPT and other LLMs. Addison-Wesley Professional, 2023 |
| Supplementary Reading | 9781800200883 | Babcock, Joseph and Bali, Raghav. Generative AI with Python and TensorFlow 2: Create images, text, and music with VAEs, GANs, LSTMs, GPT models and more: Harness the power of generative models to create images, text, and music. Packt Publishing, 2021 |
| Supplementary Reading | Use LangGraph Persistence to retain agent state across workflow steps and interactions. Practise saving context, resuming processes and managing continuing conversations so your applications can remember relevant information and support more coherent multi-step agent behaviour. | |
| Supplementary Reading | Use LangChain to build applications that connect language models with prompts, tools, data sources and structured workflows. Work with its Python components to develop practical generative AI applications and experiment with increasingly capable agent-based solutions. | |
| Supplementary Reading | Use LangGraph to build stateful AI agents and multi-step workflows using graph structures. Define states, decisions, actions and transitions, then test how an agent progresses through tasks, preserves context and coordinates different operations during execution. | |
| Supplementary Reading | Brousseau, C. and Sharp, M. (2024) LLMs in Production: From Language Models to Successful Products. Shelter Island, NY: Manning. | |
| Supplementary Reading | 9783031656460 | Kamath, Uday, Kevin Keenan, Garrett Somers, and Sarah Sorenson. Large Language Models: A Deep Dive. Springer, 2024 |
| Supplementary Reading | Iusztin, P. and Labonne, M. (2024) LLM Engineer’s Handbook: Master the Art of Engineering Large Language Models from Concept to Production. Birmingham: Packt Publishing | |
| Supplementary Reading | Use Python to write and run programs for data processing, machine learning, automation and experimentation. Install it on your computer, add packages as needed, and use it throughout practical coding activities across both technical modules. | |
| Supplementary Reading | Use Hugging Face Hub to explore models, datasets and machine learning resources in one place. Examine model information, download reusable components and connect practical AI development with resources shared by the wider machine learning community. | |
| Supplementary Reading | Use Hugging Face dataset cards to understand a dataset’s purpose, contents, structure and intended uses before working with it. Review important contextual information and use these details to make better informed choices during practical projects. | |
| Supplementary Reading | Use Python virtual environments to create separate spaces for different coding projects. Install the packages each project needs, avoid dependency conflicts and keep your practical work organised, reproducible and easier to manage throughout your studies. | |
| Supplementary Reading | Auffarth, B. and Kuligin, L. (2025) Generative AI with LangChain: Build Production-Ready LLM Applications and Advanced Agents Using Python, LangChain and LangGraph. 2nd edn. Birmingham: Packt Publishing | |
| Supplementary Reading | Use the Python Tutorial to build programming skills through clear explanations and worked examples. Follow topics progressively, practise syntax and concepts, then apply what you learn directly when writing and testing your own Python code. |
Related Programmes
| Programme | Term | Type | |
|---|---|---|---|
| 1 | MSc AI for Business Transformation | 2 | Optional |
| 2 | MSc Software Technical Leadership | 2 | Optional |
| 3 | MSc AI and Machine Learning | 1 | Core |
Module Review and Approval
| Version | Date | ReviewedBy | NextReview |
|---|---|---|---|
| 1.0 | dd MMMM yyyy | Dr Vimal Dwivedi | October 2027 |