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 leverage AI and when to exercise caution.
• Structuring team agreements: triggers, actions, evidence, and ownership.
• Defining the Prompt Curator role: validation, decision-making, and sign-off authority. Including AI incident response planning.
Day 1 — Afternoon: Constraints, Risks and Compliance
• Understanding real-world LLM capabilities and identifying prompt risk vectors: injection, data leakage, and hallucinations.
• Navigating the legal framework: GDPR, EU AI Act, and sector-specific standards (DICOM, HL7, HIPAA).
• Practical exercise: translating a domain standard into a robust prompt guardrail.
Day 2 — Morning: Technical Architecture of Prompts
• Agent architecture from a prompt design perspective: memory, context, and goals.
• API integration strategies, domain data sources, and techniques for multi-agent systems and prompt chaining.
Day 2 — Afternoon: Enterprise Prompt Anatomy
• Exploring the six core layers: Role, Context, Constraints, Domain Standards, Format, and Examples.
• Establishing prompt hierarchy: System (organization-wide), Domain (team-level), and Task (individual-level).
• Demonstration: deconstructing a naive prompt and rebuilding it effectively. Includes a team brief for Days 3–5.
Block 2 — Co-Construction Workshops (Days 3–4–5)
Day 3 — Discovery and Standards Audit
- Parallel team workshops involving Architects, Domain-Specific Developers, Back-End Engineers, and QA.
- Mapping enterprise standards and constraints to identify and resolve cross-team conflicts.
- Day 3 Deliverable: A comprehensive Standards Map and an impact/effort priority matrix.
Day 4 — Convention Design and Template Construction
- Developing naming conventions, versioning strategies, and a tag system (categorized by team, domain, and target tool).
- Creating initial validated templates for specific contexts: TypeScript DICOM, code reviews, QA testing, and API documentation.
- Day 4 Deliverable: Four or more operational templates accompanied by a conventions guide.
Day 5 — Library Assembly, Governance and Official Handover
- Structuring the library and integrating with GitHub Copilot, Cursor, or internal LLM APIs.
- Finalizing the Prompt Curator role, defining quality metrics, establishing team rituals, and drafting 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 (either introductory or advanced).
- Technical roles: Practical development experience within the company’s current technology stack.
- Management roles: Fundamental familiarity with current AI tools (such as ChatGPT, Copilot, etc.).
- Organizational commitment: Active involvement of team leaders during Days 3–5.
- Prior preparation: Availability of existing standards documentation (e.g., README files, coding guidelines).
Target 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
