• Role of GenAI in SAP’s Business AI strategy
• Embedded vs side-by-side AI scenarios on BTP
• Value of reusable AI services and models
• End-to-end GenAI lifecycle overview
• Positioning of Generative AI Hub and AI Core
• Relationship between AI services, models, and applications
• Cloud-native execution and scalability concepts
• Landscape supports enterprise-grade AI adoption
• Available service categories and capabilities
• Text, chat, embedding, and content generation services
• Service discovery and selection criteria
• Catalog enables standardized AI consumption
• Large Language Models (LLMs) concepts
• Multimodal and domain-specific models
• Model strengths, limitations, and use cases
• Model selection ensures optimal outcomes
• Authentication and authorization for AI services
• Request, response, and token handling
• Rate limits and usage considerations
• Consumption enables AI-powered applications
• Structuring instructions, context, and examples
• Managing system, user, and assistant prompts
• Improving response quality and consistency
• Prompt engineering maximizes model effectiveness
• Managing AI workflows and executions
• Monitoring model usage and performance
• Versioning and lifecycle management
• Orchestration ensures controlled AI operations
• Use in SAP Build, CAP, and RAP applications
• Event-driven and API-based integration patterns
• Embedding AI into business processes
• Integration delivers intelligent enterprise scenarios






















