Introduction to AI-Assisted Software Development
• Welcome and seminar overview
• The current state of AI in software development
• Key AI technologies relevant to software engineering
• Ethical considerations and potential biases in AI-assisted development

Automatic Code Generation
• Overview of code generation tools (e.g., Cursor, GitHub Copilot, TabNine, Amazon Q Developer)
• How these tools work: underlying models and training data
• Demonstration: Using GitHub Copilot in different programming languages

Hands-on exercise:
o Writing code with and without AI assistance
o Comparing productivity and code quality
o Effective prompting and interaction with AI coding assistants
o Balancing AI-generated code with human oversight and customisation

Discussion: Best practices, limitations, and when to use code generation

Rapid Prototyping and Interface Design
• Introduction to AI in UI/UX design
• Overview of tools: Figma AI features, Uizard, Visily and others
• Demonstration: Creating a functional prototype using AI

Hands-on exercise:
o Creating a simple app prototype from a prompt
o Creating a simple app prototype from a wireframe, sketch or screenshot

Group discussion

Intelligent Development Assistants
• AI integrations in popular IDEs (VS Code, IntelliJ, PyCharm)
• Features: code completion, code edit, refactoring suggestions, bug detection, chat with codebase
• Automated refactoring tools

Hands-on session:
o Setting up AI assistants in participants’ preferred IDEs
o Using AI-driven features in real-time coding scenarios
o Using AI to refactor and improve code quality
• Best practices for working alongside AI assistants

Code Quality and Analysis
• Introduction to AI-powered code analysis tools (e.g., SonarQube with AI features, Qodana)
• Static vs. dynamic code analysis
• AI techniques for identifying code smells and optimisation opportunities

Workshop:
o Analysing a sample codebase for optimisation opportunities
o Measuring improvements in performance and readability

Automatic Documentation
• The importance of documentation and API references in software development
• Tools for AI-generated documentation (e.g., Mintlify, DocuWriter, and others)

Exercise:
o Generating documentation for a given code sample or codebase
o Reviewing and editing AI-generated documentation
o Strategies for maintaining consistency between code and documentation

Automated Testing and Validation
• Overview of AI in software testing strategies
• AI-driven test case generation and prioritisation – techniques and tools
• Implementing intelligent fuzzing and mutation testing strategies
• Tools for AI-assisted test generation

Hands-on lab:
Creating AI-generated unit tests for a sample application
Exploring AI-powered functional and integration testing
Analysing test coverage and effectiveness
 
Integrating AI Tools in Development Workflows
• CI/CD pipelines with AI integration
• Best practices for incorporating AI tools into existing processes
• Addressing challenges: team adoption, learning curve, tool selection

Group discussion:
Sharing experiences and concerns about AI adoption
Brainstorming solutions to common integration challenges
 
Case Studies and Real-World Applications
• Examination of successful AI integration in various companies
• Lessons learned and key success factors

Group activity:
a) Designing an AI-assisted development strategy for a fictional project
b) Presentations and peer feedback
 
Future Trends and Advanced Topics
• Emerging AI technologies and their potential impact on software development
• Exploration of domain-specific language models for specialised development tasks
• The role of AI in low-code and no-code development platforms
• Preparing for the future: Skills and adaptations for AI-augmented development teams
 
Capstone Project
• Design and implement a software project leveraging AI assistance throughout the development lifecycle
• Apply AI tools for code generation, testing, and optimisation in a real-world scenario
• Present and defend your AI-assisted development strategy and outcomes