Course Outline
Block 1 — Shared Foundations (Days 1–2)
Day 1 — Morning: The Human Factor in AI Adoption for Government
• Trust and reliance calibration: determining appropriate use of AI.
• Team agreement structure: defining triggers, actions, evidence requirements, and ownership.
• Prompt Curator role: ensuring validation, decision-making, sign-off, and developing an AI incident response plan.
Day 1 — Afternoon: Constraints, Risks, and Compliance for Government
• Real LLM capabilities: identifying prompt risk vectors such as injection, data leakage, and hallucinations.
• Legal framework: understanding GDPR, EU AI Act, and sector-specific standards (e.g., DICOM, HL7, HIPAA).
• Practical exercise: translating domain standards into prompt guardrails.
Day 2 — Morning: Technical Architecture of Prompts for Government
• Agent architecture: exploring memory, context, and goals from a prompt design perspective.
• API integration and domain data sources, including multi-agent systems and prompt chaining.
Day 2 — Afternoon: Enterprise Prompt Anatomy for Government
• The six layers of prompts: Role, Context, Constraints, Domain Standards, Format, and Examples.
• Prompt hierarchy: System (organization-wide), Domain (team), and Task (individual).
• Demonstration: deconstructing a basic prompt and rebuilding it. Team briefing for Days 3–5.
Block 2 — Co-Construction Workshops (Days 3–4–5)
Day 3 — Discovery and Standards Audit for Government
- Parallel team workshops: Architects, Domain-Specific Developers, Back-End Engineers, QA Specialists.
- Mapping enterprise standards and constraints to identify cross-team conflicts.
- Day 3 Deliverable: Standards Map and impact/effort priority matrix.
Day 4 — Convention Design and Template Construction for Government
- Establishing naming conventions, versioning systems, and tagging (team, domain, target tool).
- Building the first validated templates: TypeScript DICOM, code review, QA tests, and API documentation.
- Day 4 Deliverable: Four or more operational templates and a conventions guide.
Day 5 — Library Assembly, Governance, and Official Handover for Government
- Organizing the library and integrating it with GitHub Copilot, Cursor, and internal LLM APIs.
- Defining the Prompt Curator role, establishing quality metrics, team rituals, and a 30-day deployment plan.
- Final Day 5 Deliverable: Documented Library v1.0, Governance Charter, and 30-Day Plan.
Requirements
- Completion of at least one artificial intelligence training course (either introductory or advanced).
- Technical profiles: experience in the organization’s technology stack.
- Management profiles: foundational knowledge of AI tools (such as ChatGPT, Copilot, etc.).
- Organizational commitment: active engagement of team leaders during Days 3 through 5.
- Pre-existing documentation: availability of established standards (including README files and coding guidelines).
Target Audience
- Software Architects
- Developers (domain-specific, back-end, front-end)
- Quality Assurance Engineers / Code Technicians
- Team Leaders and Middle Managers
- IT Managers, Decision-Makers, and AI Project Leads for government initiatives.
Testimonials (2)
That i gained a knowledge regarding streamlit library from python and for sure i'll try to use it to improve applications in my team which are made in R shiny
Michal Maj - XL Catlin Services SE (AXA XL)
Course - GitHub Copilot for Developers
Trainer able to adjust the course level during training to fit our understanding level on the topic, so that we could gain more useful knowledge that could further help us harness the tools in our daily works.
