Introduction to AI Agents
Adel Nehme
VP of AI Curriculum, DataCamp
Jeeves, I'm travelling to Tokyo on June 26 and staying there until July 12. Help organize my trip.
An AI model capable of reasoning, planning, and acting on a set of actions by interacting with its environment.
An AI model capable of reasoning, planning, and acting on a set of actions by interacting with its environment.
An agent is a system that leverages an AI model to interact with its environment to achieve a user-defined objective. It combines reasoning, planning, and the execution of actions (often via external tools) to fulfill tasks.
Level | Agency | Description | Examples |
---|---|---|---|
0 | No agency | Systems that can only respond based on trained knowledge or perform discrete, pre-defined tasks | Chatbots with trained knowledge (e.g. GPT-4o), workflow automation systems |
1 | Basic routing | AI models that can route scenarios in workflows | A customer support workflow where an AI model routes a ticket based on its content |
2 | Tool-using agents | Systems that can utilize external tools | A travel AI agent that can book flights (e.g. Jeeves) |
3 | Autonomous agents | Systems that can perform multiple steps autonomously | Deep research tools that can perform multi-step reasoning and tool calling |
4 | Multi agent systems | Systems that can delegate workflows to multiple agents | Coding assistants that can ideate, generate, and push code to an existing codebase |
Introduction to AI Agents