Course Outline
Module 1 — Shared Foundations (Days 1–2)
Day 1 — Morning: The Human Element in AI Adoption
• Calibrating trust and reliance: determining appropriate use cases for AI and when to halt.
• Structuring team agreements (triggers, actions, evidence, and ownership).
• Defining the Prompt Curator role: validation, decision-making, and sign-off procedures, including AI incident response planning.
Day 1 — Afternoon: Constraints, Risks, and Compliance
• Understanding actual LLM capabilities and prompt risk vectors: injection, data leakage, and hallucinations.
• Reviewing the legal framework: GDPR, the EU AI Act, and sector standards (DICOM, HL7, HIPAA).
• Practical exercise: translating domain standards into effective 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: Anatomy of Enterprise Prompts
• The six core layers: Role, Context, Constraints, Domain Standards, Format, and Examples.
• Prompt hierarchy: System (organization-wide), Domain (team-level), and Task (individual-level).
• Demonstration: deconstructing a basic prompt and reconstructing it for enterprise use, followed by briefings for Days 3–5.
Module 2 — Collaborative Construction Workshops (Days 3–5)
Day 3 — Discovery and Standards Audit
- Parallel workshops for Architects, Domain-Specific Developers, Back-End Developers, and QA.
- Mapping enterprise standards and constraints to identify cross-team conflicts.
- Day 3 Outcome: A Standards Map accompanied by an impact/effort priority matrix.
Day 4 — Convention Design and Template Development
- Establishing naming conventions, versioning controls, and tag systems (team, domain, target tool).
- Creating initial validated templates for TypeScript DICOM, code reviews, QA testing, and API documentation.
- Day 4 Outcome: Four or more operational templates plus a conventions guide.
Day 5 — Library Assembly, Governance, and Handover
- Organizing the library and integrating with GitHub Copilot, Cursor, or internal LLM APIs.
- Finalizing the Prompt Curator role, quality metrics, team rituals, and a 30-day deployment plan.
- Final Day 5 Outcome: A documented Library v1.0, a Governance Charter, and a 30-Day Deployment Plan.
Requirements
- Completion of at least one prior AI training module (introductory or advanced level).
- Technical roles: development experience with the company's current technology stack.
- Management roles: basic familiarity with AI tools (e.g., ChatGPT, Copilot).
- Organizational commitment: active engagement of team leaders during Days 3–5.
- Prior preparation: access to existing standards documentation (such as README files and coding guides).
Intended audience
- Software architects
- Developers (domain-specific, back-end, and front-end)
- QA engineers and code technicians
- Team leaders and middle management
- 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
