Hide sidebar

Agentic AI Wiki

Beginner's guide to understanding AI agents

What are Agentic AIs?

represents a paradigm shift from passive AI assistants to autonomous systems that can actively pursue goals, make decisions, and take actions to achieve objectives.

Unlike traditional AI models that simply respond to prompts, agentic AI systems can plan, reason through complex problems, and execute multi-step tasks independently. They combine with planning, memory, and tool-use capabilities to create intelligent agents that can work alongside humans.

Key Concepts

The ability of AI agents to operate independently and make decisions without constant human intervention.

The capability for AI agents to interact with external systems, APIs, and tools to accomplish tasks.

Multiple AI agents working together, often with specialized roles, to solve complex problems collaboratively.

Mechanisms that allow AI agents to store, retrieve, and use information from past interactions.

Learning Resources

Featured Videos

Intro to Large Language Models
Andrej Karpathy — 1 hour overview of how LLMs work under the hood
The Rise of AI Agents and Agentic Reasoning
Andrew Ng — BUILD 2024 Keynote on agentic workflows, planning, and multi-agent collaboration
What are AI Agents?
IBM Technology — Clear, beginner-friendly explanation of how AI agents perceive, reason, and act
Let's build GPT: from scratch, in code
Andrej Karpathy — Deep-dive coding walkthrough of the transformer architecture that powers modern LLMs

Getting Started

  1. Start by understanding the basics of
  2. Learn about to communicate effectively with AI models
  3. Explore frameworks like for building agent applications
  4. Practice building simple agents that can use tools and APIs
  5. Gradually move to more complex