Programme Content
AI Strategy, Enterprise Adoption, and Modern AI Stack
Data-driven decision-making and AI overview
Enterprise AI landscape and AI-first mindset
Generative AI impact and live demos
LLM Q&A, RAG systems, and AI agent workflows
Industry use cases and adoption challenges
Supervised and unsupervised machine learning
ML vs GenAI vs agents and agentic AI workflows
Expectation gaps and practical considerations
Data Foundation to Achieve AI Solution Architecture
Enterprise data availability and quality challenges
Translating business problems into data problems
Solution considerations and pretrained vs custom models
ML, time series models, and LLMs for forecasting
Retrieval and AI agents for forecasting
Quality and defect data management
Yield and cost control through AI
AI-driven quality monitoring and early defect identification
Process stability, rework reduction, and downtime reduction
Data-Driven Model and AI-Enabled Transformation
Operational waste and inefficiencies identification
AI-driven workflow redesign
Lean operations and maintenance integration
Human-AI interaction and collaboration
Risk and reliability assessment
Operational impact measurement
Cost savings quantification
Practical use of OpenAI-led workflows
How LLMs Reshape AI Solutions, Workflows, and Advantage
Customer segmentation and churn modeling
Classical ML techniques and clustering with XGBoost
LLM-powered personalization
LangChain orchestration and AI-driven customer workflows
Probability and logit models
Classical ML outputs as signals
LLM-driven action prioritization
Document loading, chunking, and preprocessing
Vector search basics and building RAG workflows
Foundations of Agentic AI Systems
LLMs as reasoning engines
Tools vs assistants vs agents
Agentic system architecture
Goals, memory, planning, and actions
Feedback and workflow execution
Guardrails and human oversight
Failure modes and vector databases
Agent Orchestration and Tool-Integrated AI
How tool calling works in practice
Designing controlled tool inputs and outputs
Building multi-step agent workflows
Agent output checking and validation
AI Evaluation, Reliability, and ROI
Evaluating AI output for accuracy and reliability
Improving retrieval and prompting strategies
Error handling and fallback mechanisms
Safety and guardrails
Real-world AI solution design
Copilots and agentic systems
AI-enabled workflows
Impact and ROI validation
Risk assessment and feasibility review
