Course Outline
Block 1 — Core Concepts (Days 1–2)
Day 1 — Morning: Human Elements in Artificial Intelligence Adoption
• Trust and reliance calibration: determining appropriate use cases and cessation criteria for AI systems.
• Collaborative framework establishment (trigger / action / evidence / owner).
• Prompt Curator responsibilities: validation, decision-making, and authorization. Establishment of an incident response protocol.
Day 1 — Afternoon: Regulatory Constraints, Risk Management, and Compliance
• Current large language model (LLM) capabilities — identifying prompt risk vectors such as injection attacks, data leakage, and hallucinations.
• Relevant legal frameworks: GDPR, EU AI Act — industry-specific standards (DICOM, HL7, HIPAA).
• Practical exercise: translating a domain standard into a prompt guardrail.
Day 2 — Morning: Technical Structure of Prompts
• Agent architecture: memory, context, and goals from a prompt design perspective.
• API integration and domain data sources, multi-agent systems, and prompt chaining techniques.
Day 2 — Afternoon: Enterprise Prompt Structure
• The six layers: Role / Context / Constraints / Domain Standards / Format / Examples.
• Prompt hierarchy: System (organizational-wide) — Domain (team-level) — Task (individual level).
• Demonstration: analyzing an ineffective prompt and reconstructing it. Team briefing for Days 3–5.
Block 2 — Collaborative Development Workshops (Days 3–4–5)
Day 3 — Discovery and Standards Audit
- Concurrent team workshops: Architects, Domain-Specific Developers, Back-End Engineers, and Quality Assurance.
- Mapping enterprise standards and constraints — identifying cross-team conflicts.
- Day 3 Deliverable: Standards Map + impact/effort priority matrix.
Day 4 — Convention Design and Template Construction
- Naming conventions, versioning, tag system (team, domain, target tool).
- Developing first validated templates: TypeScript DICOM, code review, QA tests, API documentation.
- Day 4 Deliverable: 4+ operational templates + conventions guide.
Day 5 — Library Assembly, Governance, and Official Handover
- Library organization, GitHub Copilot / Cursor / internal LLM API integration.
- Prompt Curator role, quality metrics, team rituals, 30-day deployment plan.
- Final Day 5 Deliverable: Documented Library v1.0 + Governance Charter + 30-Day Plan for government.
Requirements
- Completion of a minimum of one artificial intelligence training module, whether introductory or advanced in scope.
- Technical roles: Demonstrated development proficiency within the organization's specific technology stack.
- Management roles: Foundational knowledge of generative AI applications (e.g., ChatGPT, Copilot).
- Organizational commitment: Active engagement by team leaders during sessions 3 through 5.
- Pre-existing assets: Availability of current standards documentation, 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
Testimonials (1)
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
