Kick off and AI landscape
- Overview of AI-assisted development tools and capabilities
- Demonstration of model comparison tools and prompting approaches
- Productivity gains versus quality and security trade-offs
- Group discussion on current AI usage in development workflows
- Lab: evaluating AI-generated code quality
- Analyse AI-generated outputs against a structured checklist
- Identify correctness, maintainability, and security issues
- Annotate and prioritise findings based on risk
Challenge exercise: task management API
- Generate a task manager with dependencies and scheduling logic
- Detect circular dependencies and resource conflicts
- Evaluate implementation against business requirements
- Apply structured code review techniques
Understanding AI quality pitfalls
- Common failure patterns in AI-generated code
- Hallucinated APIs and incorrect assumptions
- Hidden complexity and over-engineering
- Missing edge cases and inconsistent logic
- Maintaining coding standards across human and AI contributions
- Integrating linters, formatters, and automated code review tools
- Discussion on pull request and review practices
Lab: testing and refactoring AI code
- Generate and execute AI-created unit tests
- Identify gaps in test coverage and missing scenarios
- Validate behaviour across edge cases such as invalid inputs and concurrency
- Refactor code for clarity, modularity, and maintainability
- Implement logging, error handling, and performance improvements
Challenge exercise: e-commerce pricing engine
- Build pricing logic with discounts, tax, and promotions
- Identify issues such as incorrect calculations and edge cases
- Improve test coverage and ensure deterministic outcomes
- Apply static analysis and quality gates
Security in AI assisted development
- Introduction to OWASP Top 10 risks in AI-generated code
- Common vulnerabilities in authentication, data handling, and APIs
- Security scanning and dependency analysis tools
- Aligning secure coding practices with AI workflows
Lab: spot and fix vulnerabilities
- Analyse AI-generated user management system
- Identify vulnerabilities including:
- Broken access control
- Weak cryptographic practices
- Injection flaws
- Authentication weaknesses
- Compare manual review with automated security tool outputs
- Implement secure coding fixes
- Parameterised queries
- Strong password hashing
- Input validation and sanitisation
- Secure token handling
Security testing and validation
- Create test cases to simulate attacks
- Perform basic penetration testing scenarios
- Validate fixes against security requirements
Advanced exercise: multi-factor authentication
- Extend system with secure authentication mechanisms
- Address edge cases and timing attack risks
- Ensure usability and security balance
Governance, IP and compliance
- Code provenance and AI-generated content considerations
- Licensing risks and intellectual property concerns
- Data protection and organisational AI policies
- Establishing responsible AI development practices
Group exercise: responsible AI coding policy
- Define organisational standards for AI tool usage
- Create policies covering:
- Tool selection and approval
- Code attribution and IP protection
- Quality and security gates
- Developer training and competency
- Incident response and audit processes
Industry scenario workshops
- Financial services, healthcare, government, and retail contexts
- Identify regulatory and compliance requirements
- Balance productivity with risk management
Policy presentation and synthesis
- Present and critique team policies
- Consolidate best practices
- Define implementation roadmap and success metrics
Wrap up and key takeaways
- Reinforce critical evaluation of AI-generated code
- Align learning to real-world application
- Define next steps within AI in software development pathway
Exams and assessments
There are no formal exams included in this course. Learners will be assessed through practical labs, group exercises, and instructor-led discussions. These activities are designed to validate understanding and ensure learners can apply concepts in real-world scenarios.
Hands-on learning
This course includes:
- Scenario-based labs using AI-generated code
- Real-world exercises focused on quality and security challenges
- Instructor-guided refactoring and secure coding practices
- Collaborative group workshops to apply governance frameworks
