Skip to content
InfratoApp

NVIDIA · Course

Agentic AI Explained (self-paced)

Agentic AI Explained is a short NVIDIA Deep Learning Institute course introducing autonomous software agents that perceive, reason, act and learn. It covers what makes AI agentic, the building blocks of agents, design patterns, real-world uses and frameworks.

Open at NVIDIA ↗Common questions

Who it suits

  • Anyone who wants a clear definition of agentic AI and a tour of how agent systems are built.
  • People with basic programming (especially Python) or a technical or data science background; some ML or automation knowledge helps.

What it covers

  • What makes AI agentic, and how agentic and generative AI work together.
  • The core traits of an agent, agentic architecture, engineering principles and design patterns.
  • Agent roles and collaboration, and real-world applications.
  • Building and scaling agents, frameworks and tools, and current trends.

Before you start

  • A basic understanding of programming (especially Python), or familiarity with core ideas in mathematics or data science.
  • Some knowledge of machine learning, automation or AI principles can help.

Common questions about Agentic AI Explained (self-paced)

How long is it?
NVIDIA lists a duration of one hour, in 13 modules of lectures and videos.
Does it cost anything?
NVIDIA lists the price as free, and says free courses are available for enrolment worldwide.
What will I be able to do?
NVIDIA lists defining what makes AI agentic, recognising the building blocks of agentic systems, exploring real-world applications and starting to build a simple agent.

More like this

Keep learning on Infrato

Where this comes from

Written from NVIDIA’s own pages, read on 2026-10-13. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with NVIDIA and this is not an endorsement.