Security, Ethics and Governance

_{Module 1}

Unlocking AI potential in product development

• AI's impact on software engineering
• AI for requirements and design
• AI for building and testing
• AI for deploying and monitoring
• Defining your people, processes, and tools
• Identifying and prioritising use cases
• Developing a business case
• Governance and security for new AI initiatives
• Measuring the business value of new AI initiatives

_{Module 2}

AI for programming

• Introduction to programming with large language models
• AI as a programming co-pilot
• Debugging and problem solving with LLMs
• Reviewing and refactoring code with LLMs
• Generating testing suites with LLMs
• AI for documentation and explanation
• Context engineering and personas
• Data security and governance when programming with AI
• Your AI solutions as products

_{Module 3}

Designing and building AI products

• Architecting AI-enabled solutions
• The modern AI developer's tech stack
• AI-assisted technical design and prototyping
• Implementing the core AI component
• Advanced AI orchestration with frameworks
• Managing state and context with MCP (model control plane)
• Integrating AI components with legacy systems
• Debugging and testing AI-enabled software
• Optimising for performance, cost, and quality
• Efficient, effective, and secure AI usage

_{Module 4}

Driving product quality with AI

• Factors affecting product quality
• Estimating and mitigating project risk
• Principles of software security and resilience
• Using AI for vulnerability scanning
• Challenges of testing AI systems
• AI-generated testing for traditional code
• Testing and evaluating LLM outputs
• Ethics and inclusion in quality assurance
• The business value of quality assurance

_{Module 5}

Crafting data for knowledge-aware AI

• Introduction to machine learning
• Data sourcing for AI
• Data management processes
• Preparing data for AI retrieval
• Data chunking and indexing
• Working with APIs
• Building retrieval-augmented generation (RAG)
• Legal and ethical data standards
• Improving data practices for AI-driven products

Driving Business Value with AI Solutions

_{Module 6}

Product deployment and maintenance: DevOps and MLOps

• The culture of continuous integration
• Continuous integration tooling and practice
• Cloud deployment strategies
• Containerised deployment with Docker
• Introduction to MLOps and LLMOps
• Container orchestration with Kubernetes
• Monitoring and evaluating live LLMs
• Ethical and environmental considerations in product deployment
• Continuous improvement and sharing best practices

_{Module 7}

Championing adoption of AI-driven software

• Leading internal product strategy
• Managing change
• Data-driven decision making
• Ensuring stakeholder buy-in
• Creating your product adoption strategy
• Presenting your product adoption strategy
• Effective project reporting
• Evaluating project learnings
• Creating lasting impact with AI initiatives

_{Module 8}

Capstone project and end point assessment

The capstone project requires learners to deliver a quantifiable generative AI end-product that solves a complex business problem, integrating AI into processes and deploying a live application with continuous monitoring. The project also focuses on providing value through quantifiable ROI, securing organisational change with a data-driven adoption strategy, and addressing ethical implications through responsible AI governance.