Agentic AI Design using AMD Technology

Building trustworthy and capable agentic AI systems requires open innovation, scalable computing, and transparent design. This workshop explores how open-source initiatives – with AMD as a key driver – are accelerating the development of autonomous AI agents. It also highlights how AMD Agent Computers with integrated GPUs support efficient on-device inference and agentic workloads.

Participants will follow the evolution from token generation to AI agents, refresh the fundamentals of context engineering and RAG, and explore the main components of an AI agent: the model, orchestration, and tools. Guided hands-on labs will be delivered through the AUP Learning Cloud.

Benefits for the attendees, what will they learn:

• Understand how generative AI has evolved into agentic systems.
• Learn how context engineering, RAG, models, orchestration, and tools work together.
• Gain hands-on experience with agentic AI concepts through practical labs.
• Understand how integrated GPUs support efficient on-device AI workloads.
• Gain knowledge applicable to research, education, and future AI projects.

Level

Introductory to intermediate. Basic familiarity with AI and generative AI is recommended. Basic Python knowledge is helpful but not required. Participants need a computer, a stable internet connection, and an up-to-date web browser.