Course Outline
Block 1 — Shared Foundations (Days 1–2)
Day 1 — Morning: The Human Factor in AI Adoption
• Trust and reliance calibration: determining when to use AI and when to discontinue usage.
• Structuring team agreements (trigger, action, evidence, owner).
• Defining the Prompt Curator role: validation, decision-making, and sign-off. Developing an AI incident response plan.
Day 1 — Afternoon: Constraints, Risks, and Compliance
• Understanding real LLM capabilities and prompt risk vectors: injection, data leakage, and hallucinations.
• Legal framework review: GDPR, EU AI Act, and sector standards (DICOM, HL7, HIPAA).
• Practical exercise: translating domain standards into prompt guardrails.
Day 2 — Morning: Technical Architecture of Prompts
• Agent architecture from a prompt design perspective: memory, context, and goals.
• API integration, domain data sources, multi-agent systems, and prompt chaining.
Day 2 — Afternoon: Enterprise Prompt Anatomy
• The six layers: Role, Context, Constraints, Domain Standards, Format, and Examples.
• Prompt hierarchy: System (organization-wide), Domain (team-level), and Task (individual).
• Demonstration: deconstructing a naive prompt and rebuilding it effectively. Team briefing for Days 3–5.
Block 2 — Co-Construction Workshops (Days 3–4–5)
Day 3 — Discovery and Standards Audit
- Parallel team workshops for Architects, Domain-Specific Developers, Back-End, and QA.
- Mapping enterprise standards and constraints, including the identification of cross-team conflicts.
- Day 3 Deliverable: Standards Map and an impact/effort priority matrix.
Day 4 — Convention Design and Template Construction
- Establishing naming conventions, versioning, and tagging systems (team, domain, target tool).
- Developing initial validated templates for TypeScript DICOM, code review, QA tests, and API documentation.
- Day 4 Deliverable: Four or more operational templates plus a conventions guide.
Day 5 — Library Assembly, Governance, and Official Handover
- Organizing the library and integrating with GitHub Copilot, Cursor, or internal LLM APIs.
- Defining the Prompt Curator role, quality metrics, team rituals, and the 30-day deployment plan.
- Final Day 5 Deliverable: Documented Library v1.0, Governance Charter, and 30-Day Plan.
Requirements
- Completion of at least one prior AI training module (introductory or advanced).
- Technical profiles: Development experience within the company’s technology stack.
- Management profiles: Basic familiarity with AI tools such as ChatGPT or Copilot.
- Company commitment: Active participation from team leaders during Days 3–5.
- Prior provision: Access to existing standards documentation (e.g., README files, coding guides).
Target audience
- Software architects
- Developers (domain-specific, back-end, front-end)
- QA 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
