Introduction to LLM Agents
Chapter 1: What Are LLM Agents?
From LLMs to Intelligent Action
Moving Past Simple Chatbots
What Exactly Is an LLM Agent?
The Purpose of LLM Agents
Comparing Agents to Scripts
Illustrative Agent Applications
Understanding Agent Independence
Quiz for Chapter 1
Chapter 2: The Building Blocks of an LLM Agent
The Central Role of the LLM
Crafting Instructions for Agents
Giving Agents Abilities
Remembering Recent Events
Thinking Before Acting
The Agent's Operational Loop
A Simplified Agent Workflow
Quiz for Chapter 2
Chapter 3: Your First LLM Agent: A Step-by-Step Guide
Preparing Your Workspace for Agent Development
Selecting an LLM for Your First Agent
Instructing Your Agent for a Task
Specifying the Agent's Goal
Coding the Agent's First Action
Executing and Monitoring Your Agent
Addressing Initial Problems
Hands-on Practical: Creating a To-Do List Agent
Quiz for Chapter 3
Chapter 4: Equipping Agents With Tools
Understanding Agent Tools
The Necessity of Tools for Agents
Creating a Basic Tool: A Calculator Example
Connecting Tools to Your Agent
Prompting Agents to Utilize Tools
Agent Tool Selection Logic
Survey of Available Tool Categories
Hands-on Practical: Equipping Your Agent with Search
Quiz for Chapter 4
Chapter 5: Basic Agent Planning and Execution
What is Agent Planning?
Guiding Agent Reasoning with Chain-of-Thought
Introducing the ReAct Approach
Setting Clear Objectives for Agents
Decomposing Complex Tasks
Tracking Task Execution
Managing Basic Execution Failures
Practice: Building a ReAct Agent for Sequential Tasks
Quiz for Chapter 5
Chapter 6: LLM Agent Memory: Remembering Information
Why Agents Need to Remember
A Look at Different Memory Systems
Focusing on Conversational Context
A Simple Implementation of Short-Term Memory
The Influence of Memory on Agent Behavior
Understanding Short-Term Memory Boundaries
Hands-on Practical: Adding Contextual Memory to Your Agent
Quiz for Chapter 6
Thinking Before Acting
New · Open Source
Kerb - LLM Development Toolkit
Python toolkit for building production-ready LLM applications. Modular utilities for prompts, RAG, agents, structured outputs, and multi-provider support.
Was this section helpful?
© 2025 ApX Machine LearningEngineered with