GenAI Fundamentals

• Introduction to GenAI

• Key differences between traditional AI and GenAI models

• Model types: LLMs, diffusion models, multimodal models

• What is a prompt and its components

• Leading LLM models in the market

• Public models vs. private environments

Knowledge Bases for AI Models

• Context and its limitations

• Conversation history

• Textual document sources

• Relational databases

• Embedding models

• Vector databases

• RAG architecture (Retrieval-Augmented Generation)

• Model response quality based on provided data

Use Case Identification and Definition

• GenAI project milestones

• Role and responsibilities of business stakeholders

• Understanding business processes

• Identifying pain points, defining business value, and ROI evaluation

• Data sources overview

• Data handling strategies and knowledge base definition

• Data ingestion services

• Data retrieval services

• Project risk assessment

GenAI Project Scoping

• Business validation and fine-tuning

• Ongoing quality testing

• Version management

• KPI definition

• MVP definition

• Full project definition

• Key milestones planning

Agents, Tools, and Platforms

• Chatbots

• AI agents / Agentic AI

• GenAI workflows (flows)

• Using GenAI tools within agents

• MCP servers

• Model monitoring, tracking, and control

• Leading platforms in the Agentic AI ecosystem

Final Exercise: Business Specification & Requirements Document

• Full business case development

• Technical requirements specification

• Project timeline and milestones

• Success criteria and measurement framework