Welcome to the Head of Engineering Challenge Workshop. This event has been pulled together to provide practical AI coding existing experience through progressive challenge based learning, working in teams of 2-3, focusing on real-world government service development scenarios.
- Challenge-Based Learning: Progressive 10-level challenge system with increasing difficulty and scoring
- Practical AI Experience: Hands-on experience with modern AI development tools including Claude Code, Kiro/Q Developer, and others
- Production-Ready Practices: Focus on maintainable, scalable, and secure solutions suitable for government services
- Collaborative Problem Solving: Team-based challenges tackling real government service scenarios
- Knowledge Transfer: Create lasting resources for continued AI-assisted development across departments
- 10-Level Challenge System - Progressive challenges from Level 1 to Level 10
- Level 1-3: Foundation challenges (Digital transformation, data processing, data modeling)
- Level 4-6: Intermediate challenges (Legacy modernization, business logic, security)
- Level 7-10: Advanced challenges (Performance, testing, architecture, production deployment)
| Challenge Name | Difficulty Level |
|---|---|
| PDF to Digital Service Transformation | Level 1 |
| Data Processing & Visualisation | Level 2 |
| Database-Backed CRUD Operations | Level 3 |
| Legacy Code Modernisation | Level 4 |
| Complex Business Logic Implementation | Level 5 |
| Security Vulnerability Assessment & Remediation | Level 6 |
| Performance Investigation & System Resilience | Level 7 |
| Adaptive Testing Strategy & Risk-Based Quality Engineering | Level 8 |
| Multi-Service Architecture Design | Level 9 |
| Production Deployment & Incident Response | Level 10 |
| Time | Session | Summary |
|---|---|---|
| 09:00-09:30 | Optional AI Clinic | Optional support session for tooling setup, challenge selection guidance, and individual help getting started |
| 09:30-10:15 | Challenge Kick-Off | Introduction to 10-level challenge system, scoring explained, overview of available challenges, AI tools and prompting best practices refresher |
| 10:15-12:30 | Challenge Sprint 1 | Individual hands-on development working through selected challenges (Levels 1-10), facilitator support available, focus on practical implementation |
| 12:30-13:30 | Lunch | Working lunch with informal discussions, peer support and knowledge sharing encouraged |
| 13:30-15:30 | Challenge Sprint 2 | Final development push, challenge completion and documentation, consolidation of learning and insights |
| 15:30-16:15 | Group Feedback & Scoreboard Review | Collaborative discussion on tool effectiveness, successful approaches, prompting strategies, key insights, challenge completion scoring, and peer recognition with awards |
| 16:15-16:30 | Wrap-Up & Next Steps | Summary of collective learnings, resources for continued development, event conclusion |
All materials in this repository consider public sector requirements:
- Security: Government security standards and data protection requirements
- Accessibility: WCAG compliance and inclusive design principles
- Transparency: Open source approaches and auditable development practices
- Scalability: Patterns suitable for citizen-facing services at scale
- Compliance: GDS standards and cross-government best practices
While tool-agnostic in approach, the workshop focuses on:
- Claude Code Anthropic's development-focused AI assistant
- Amazon Q Developer: AWS-integrated development assistant (formerly CodeWhisperer)
- Kiro: AI-powered development assistant
- GitHub Copilot: Traditional IDE-integrated assistance
- Cursor: AI-first development environment
- Example Government AI SDLC MCP Server: https://github.com/Version1/uk-gov-example-ai-sdlc
- Example Government Standards MCP Server: https://github.com/Version1/uk-gov-tech-standards-mcp
- Spec-Kit: Github Spec-Kit
This repository serves as both a workshop resource and a long-term reference for AI-assisted development in government contexts. We hope it provides lasting value for your teams and projects!