AI Agents
From Chat to Action

A chatbot talks. An agent acts. Learn how LLMs use tools, plan steps, and interact with the real world.

What makes an Agent?

Agents add three superpowers to standard LLMs: Planning, Memory, and Tools.

Tools

(Click to reveal)

Capability

Agents can call external functions (APIs, Calculators, Google Search) to do things the LLM can't do alone.

Planning

(Click to reveal)

Decomposition

Breaking a big goal ("Book a vacation") into smaller, manageable steps ("Search flights", "Book hotel").

Memory

(Click to reveal)

Context

Short-term memory (conversation history) and Long-term memory (Vector DBs) allow agents to remember past actions.

ReAct

(Click to reveal)

Reason + Act

A prompting pattern where the model "Thinks" about what to do, "Acts" (calls a tool), and "Observes" the output.

Interactive: The Agent Loop

Step through the lifecycle of an autonomous agent solving a problem.

Goal: "What is the weather in Tokyo?"
1. Thought
2. Action
3. Observation
Final Answer

Start the Engine

Click on the nodes in the circle (Thought -> Action -> Observation) to simulate the agent's reasoning.

Inside the Agent

How Agents Think

Agents use advanced prompting strategies to break down complex tasks.

Chain of Thought

Thinking step-by-step to avoid logical errors.

Tree of Thoughts

Exploring multiple possibilities (branches) and selecting the most promising one.

Reflexion

Reviewing past actions to self-correct ("Wait, that search failed, let me try a different keyword").

Knowledge Check

Test your Agentic knowledge.

1. What is the key difference between a Chatbot and an Agent?

2. What does "ReAct" stand for?

3. Why does an agent need "Memory"?