Develop AI Agents

Generative AI is a branch of AI that enables software applications to generate new content; often natural language dialogs, but also images, video, code, and other formats. The ability to generate content is based on a large language model (LLM), which has been trained with huge volumes of data - often documents from the Internet or other public sources of information.

AI agents build on generative AI to encapsulate:

• An LLM that acts as the agent’s “brain” - giving it language generation and reasoning capabilities.
• Instructions that specify the agent’s purpose, defining a “job description” that identifies what it can (and can’t) do.
• Tools that the agent can use to access the knowledge it needs, or to automate tasks.

By combining these three elements, an agent can not only engage with a user in a chat session; it can operate autonomously on the user’s behalf to take action.

Tip: You can try the Computing History agent shown in this video for yourself!

Ask Anton

Ask me about the relationship between LLMs and agents. I can help you understand how LLMs work, and how agents use them to interpret instructions and reason about tasks.

Learn more

This video is taken from the AI concepts for developers and technology professionals learning path in AI Skills Navigator.