AI-101 serves as a comprehensive gateway to Python programming for Artificial Intelligence and Low Code Agentic AI Development and prepares you for L1:P1-LCF and L1:P2-FMP certifications. This foundational course emphasizes modern Python programming skills with static typing—a cornerstone of robust, scalable AI projects. You'll design robust n8n workflows, and orchestrate plan-act-observe agent loops that call tools, keep memory, and respect guardrails. The curriculum spans foundational agentic concepts through advanced techniques including Model Context Protocol (MCP) and Retrieval-Augmented Generation (RAG), and deployment (self-hosted or cloud).

AI-201 introduces students to the core principles and practices of Agentic AI development. The course explores foundational theories underlying intelligent agent behaviour and provides extensive hands-on experience developing context-aware AI agents using the OpenAI Agents SDK. Through a balanced approach combining theoretical grounding with practical implementation projects, students will develop the expertise necessary to design and deploy functional multi-agent systems.

Building upon the foundation established in AI-201, this course introduces advanced Agentic AI concepts with particular focus on Model Context Protocol (MCP), Agentic Memory, and Agentic RAG. Students will study established agentic design patterns for building effective agents.

AI-220 focuses on Agentic Web theory and the practical implementation of Agent-to-Agent (A2A) Protocol systems. Students will explore how intelligent agents interact across web-based environments, share contextual information, and collaborate effectively on distributed computational tasks. The course examines core design principles for building web-native, cooperative AI systems and demonstrates how A2A protocols enable real-time communication between agents operating in diverse environments.

This advanced course focuses on cloud-first development methodologies for Agentic AI systems. Students will explore scalable, distributed AI architectures utilizing industry-standard containerization and orchestration technologies including Docker and Kubernetes for deploying AI Agents and MCP Servers. Through comprehensive hands-on projects, students will design and deploy production-ready AI applications optimized for cloud environments.

The capstone course in distributed AI systems covers enterprise-grade distributed application runtime environments, focusing on Distributed Application Runtime (Dapr) implementation alongside managed database systems and messaging architectures. Students will design and implement planet-scale AI agent networks capable of operating across global distributed infrastructure.

Artificial intelligence (AI) has experienced remarkable advancements in recent years. However, the future of AI extends beyond the digital space into the physical world, driven by robotics. This new frontier, known as "Physical AI," involves AI systems that can function in the real world and comprehend physical laws. This marks a notable transition from AI models confined to digital environments. Humanoid robots are poised to excel in our human-centred world because they share our physical form and can be trained with abundant data from interacting in human environments. This course provides an in-depth exploration of humanoid robotics, focusing on the integration of ROS 2 (Robot Operating System), Gazebo Robot Simulator, and NVIDIA Isaac™ AI robot development platform. Students will learn to design, simulate, and deploy advanced humanoid robots capable of natural interactions. The curriculum covers essential topics such as ROS 2 for robotic control, simulations with Gazebo and Unity, and using OpenAI's GPT models for conversational AI. Through practical projects and real-world applications, students will develop the skills needed to drive innovation in humanoid robotics.