Audience
- Managers and professionals who want a structured approach to generative AI.
- Consultants, trainers and analysts handling substantial written information.
- Business teams preparing to introduce AI-assisted working practices.
AI & technology
Generative AI & Large Language Models
Understand generative AI and use language models in practical business contexts.
Learning with a practical purpose.
Develop a practical understanding of generative AI and large language models, with an emphasis on useful business work. This module explores how models respond to instructions and supplied context, why fluent answers can still be wrong, and how to judge whether a proposed use actually improves an existing task.
You will create a repeatable workflow for a bounded activity such as preparing a briefing, reviewing a document or organising research notes. Through structured experiments, you will compare prompts, check evidence and design a human review process. The goal is a dependable way of working that a colleague can follow, rather than a collection of isolated prompt tricks.
Live onlineTeaching through Kent Business College, UK
2 hoursOne live session each teaching week
14 sessionsA semester for each module
28 live hoursPer module, plus independent study
The outline below is a 14-session online module, with one two-hour live session each teaching week. Reading weeks, breaks and additional activities follow the agreed cohort calendar. The cohort syllabus, full route, dates, fees, independent study and assessment requirements are confirmed before enrolment.
Who this module is designed for.
Starting knowledge and preparation
- Confidence using everyday digital tools and working with documents.
- No programming experience is required for the core activities.
- Access to non-confidential material suitable for practical exercises.
What you will work towards.
- Explain core language-model concepts in terms relevant to a business decision.
- Choose a bounded use case with clear benefits, constraints and acceptance criteria.
- Design prompts and context that produce useful, reviewable outputs.
- Compare results using a consistent rubric and evidence-based checking.
- Create a documented AI-assisted workflow with human responsibility and improvement measures.
Explore the 14-session learning plan.
Explore the focus and practical output of each teaching session. Open individual sessions below, or expand the complete plan.
Session 01 What generative AI can contribute
Examine common business tasks and distinguish useful assistance from claims that require evidence or specialist judgement.
Practical output: A shortlist of suitable use cases.
Session 02 Language models in plain English
Explore tokens, context and probabilistic generation using simple experiments with wording and supplied information.
Practical output: A model-behaviour observation log.
Session 03 Selecting a worthwhile business task
Define the current process, intended improvement and quality requirements for one manageable AI-assisted activity.
Practical output: A use-case brief and baseline.
Session 04 Clear instructions and useful constraints
Specify the audience, purpose, format and boundaries of a response, then compare alternative prompt designs.
Practical output: A reusable task prompt.
Session 05 Supplying and organising context
Select relevant background material and structure it so the model can distinguish instructions from source content.
Practical output: A task-specific context pack.
Session 06 Examples and structured outputs
Use examples and explicit output structures to make responses easier to compare, review and reuse.
Practical output: A structured-output template and checks.
Session 07 Drafting, editing and adapting material
Develop a document through separate drafting and review stages while preserving the intended meaning and audience.
Practical output: An annotated draft-and-review workflow.
Session 08 Summarising without losing important detail
Compare summaries against the source, paying attention to omissions, numbers, qualifications and conflicting statements.
Practical output: A source-checking rubric.
Session 09 Research assistance and evidence
Separate generated suggestions from verified claims and build a clear trail back to supporting material.
Practical output: An evidence-linked briefing exercise.
Session 10 Comparing models and prompts
Run the same task across controlled variations and score quality, consistency and effort using a common rubric.
Practical output: A comparative evaluation report.
Session 11 Confidentiality and information boundaries
Map what information the workflow needs and identify material that requires permission or a different handling process.
Practical output: A practical information-handling checklist.
Session 12 Designing the human review
Allocate responsibility for checking facts, judging suitability and approving the output before it is used externally.
Practical output: A review and approval procedure.
Session 13 Business-workflow project workshop
Combine prompts, context, evaluation and review into a repeatable workflow that another colleague can follow.
Practical output: A complete AI-assisted workflow pack.
Session 14 Demonstration and measured improvement
Demonstrate the process and compare its output quality and effort with the original baseline.
Practical output: A final demonstration and adoption recommendation.
Apply the learning
An evidence-based business briefing workflow
Create a repeatable process for turning a small set of approved source documents into a briefing for a defined audience. Include prompt templates, a source-checking method and a final human approval. Compare the result with an unaided or existing approach using a clear quality rubric and recorded effort.
Your project evidence can include
- A use-case brief and reusable prompt-and-context pack.
- An evaluated example briefing with source checks.
- A workflow guide, review checklist and improvement proposal.
Use anonymised, public or suitable synthetic material where workplace information is confidential. The issued assessment brief confirms the required evidence.
Assessment, feedback and certification.
- Practical tasks assess prompt design, source checking and interpretation of model behaviour.
- The project is judged on usefulness, repeatability and evidence supporting the claimed improvement.
- A short presentation explains which decisions remain with the person reviewing the output.
Teaching and the relevant course certificate are provided through Kent Business College in the UK. Completion requirements are set out in the module information; attendance alone should not be assumed to meet every assessment requirement.
Questions worth asking.
Is this a technical programming course?
No. The core route is designed for professional users. Technical implementation is covered in the AI Engineering and AI Agents modules.
Will I learn one particular AI product?
You will practise transferable methods for instructions, context, evaluation and review. The tools used for teaching are confirmed with the cohort.
Can a model guarantee factual accuracy?
No. The module teaches verification against appropriate sources and a review process matched to the consequences of using the output.