Python fundamentals, development environment setup, and best practices Data structures, file handling, exception handling, and object-oriented programming Functions, modules, and reusable Python workflows Data processing and automation for AI applications AI-assisted coding, debugging, and development using modern coding tools

Foundations of Generative AI and modern AI systems Large Language Models (LLMs), transformers, embeddings, and vector representations Prompt engineering and context engineering fundamentals Agentic AI concepts including reasoning, planning, memory, and tool use Enterprise applications of Generative AI and intelligent AI agents

Advanced prompt engineering and context engineering strategies Retrieval-Augmented Generation (RAG) using vector databases and embeddings Fine-tuning techniques and LLM evaluation Building enterprise-ready AI applications with LangChain Developing multimodal AI applications using text, image, and document understanding

Foundations of Model Context Protocol (MCP) Building secure and reliable AI workflows with MCP Connecting AI applications with enterprise tools, APIs, and external systems Authentication, authorization, and secure AI integrations Best practices for scalable, reliable, and context-aware AI applications

Practice building Generative AI solutions on Azure from setup to evaluation. Cover AI environments, model deployment, Foundry SDK, prompt flow, RAG workflows, fine-tuning, responsible AI, and Azure AI Studio tools used to test and improve application performance.

Design intelligent AI agents capable of reasoning, planning, and autonomous task execution Build multi-agent systems using LangGraph and CrewAI Agent memory, orchestration, and workflow management Develop collaborative AI agents for complex enterprise workflows Build production-ready AI agent applications

LLMOps lifecycle, deployment strategies, and AI infrastructure Monitoring, observability, evaluation, and optimization of AI applications Versioning, scalability, and production monitoring Cloud deployment using AWS services AI governance, security, and operational best practices

Deploy production-ready AI applications using modern deployment frameworks Monitor AI applications with observability, analytics, and feedback mechanisms Apply AI governance, responsible AI principles, and risk management practices Scale secure and reliable AI solutions for enterprise environments

Learn how to connect AI agents with enterprise knowledge using Foundry IQ. You'll explore how Retrieval Augmented Generation (RAG) solves the knowledge problem for AI agents, discover how Foundry IQ provides a shared knowledge platform that multiple agents can access, improve retrieval quality through data optimization, and configure agent instructions for consistent, cited responses.

Design and build an end-to-end Generative AI and Agentic AI application Apply RAG, MCP, LangGraph, CrewAI, and orchestration frameworks to solve real-world problems Deploy a production-ready AI solution using industry best practices Build a portfolio-ready project showcasing practical AI engineering skills