Leanpub Header

Skip to main content

Building AI Agents with Ollama: A Practical Course

Design, Build, and Deploy Production-Ready Local AI Agents with Ollama

The instructor has published 100% of this course.Last updated on 2026-07-29

Build powerful AI agents without relying on the cloud. In this hands-on course, you'll learn how to create intelligent, production-ready agents that run entirely on your own hardware using Ollama. Starting with the fundamentals and progressing to advanced topics like RAG, tool calling, long-term memory, and multi-agent systems, you'll develop real-world applications through practical, copy-and-run examples. Whether you're building personal assistants, automation tools, or sophisticated AI workflows, this course gives you the knowledge and code to build fast, private, and reliable AI agents with confidence.

Minimum price

$129

$179

You pay

Author earns

$

Also available for 1 course credit with a Learner Membership

PDF
EPUB
WEB
About

About

About the Course

This course teaches you how to design, build, and deploy production-grade AI agents that run entirely on your own hardware using Ollama as the inference engine. You will learn everything from installing Ollama and selecting models through advanced techniques like retrieval-augmented generation (RAG), tool calling, memory systems, multi-agent architectures, and secure deployment. Every section includes complete, working code examples you can copy, run, and extend. Whether you are building personal assistants, coding agents, document analysis tools, or autonomous workflow systems, this course provides the patterns and implementations needed to make them work reliably in the real world.

Instructor

About the Instructor

Steve Publications

Steve is a technology professional with more than 20 years of experience in software development, server infrastructure, cybersecurity, vulnerability research and reverse engineering. Throughout his career, he has designed, secured, analyzed and tested complex software and infrastructure, with a particular focus on understanding how systems fail and how they can be made more secure.

Outside of work, Steve enjoys sharing knowledge with the technology community. He collaborates with researchers, industry experts and technology professionals to write practical books covering software development, cybersecurity, cloud computing, networking, DevOps, artificial intelligence and enterprise technologies. His books focus on practical learning through clear explanations, real-world examples and hands-on exercises. With more than two decades of industry experience, his goal is to help IT professionals, students and technology enthusiasts build useful skills and stay current in a rapidly changing industry.

We believe readers deserve to know how our books are created. Most of our authors are not native English speakers, so we use AI to help translate, proofread manuscripts, fix grammar, improve sentence structure and make technical explanations easier to read. AI is used as an editing tool only. It does not replace the research, technical knowledge or hands-on experience behind our books. Some of our authors also prefer to remain anonymous for privacy or professional reasons. In those cases, we publish their work under a different name. The author's name may be different, but the quality of the content and our review process remain the same.

Every book is written, reviewed and maintained by experienced technology professionals, with contributions from our private technical community of more than 420 engineers and researchers. We spend far more time validating technical accuracy and keeping our content up to date than generating text. We are always interested in working with experienced professionals who have deep expertise in a particular technology or domain. If you would like to publish a book with us or help review an existing manuscript, we'd love to hear from you. Send us a message describing your area of expertise. We are especially interested in niche technologies, specialized skills and emerging topics that are underrepresented in existing technical literature.

If you look through the contents of our books, you'll see practical examples, detailed explanations and material that is regularly updated. Our goal is to publish books that professionals can actually rely on, not low-effort AI-generated content. If you ever feel that one of our books does not meet that standard, Leanpub offers a 60-day money-back guarantee. Feel free to request a refund if you are not satisfied with your purchase.

Material

Course Material

  • Building AI Agents with Ollama: A Practical Course

  • Who This Course Is For

  • What You Will Learn

  • How This Course Is Structured

  • Key Takeaways from This Introduction

  • Lesson 1: Foundations of Local LLMs and Ollama

  • Why Local AI Matters

  • What Is an AI Agent?

  • How Local Inference Works

  • Understanding GGUF and Quantization

  • Installing Ollama

  • Basic Installation

  • GPU Configuration

  • Docker Deployment

  • Understanding the Ollama API

  • Core Endpoints

  • Streaming Responses

  • OpenAI-Compatible Endpoint

  • Your First Agent: A Minimal Example

  • Project Setup

  • The Minimal Agent

  • How It Works

  • Running and Testing

  • Common Pitfalls

  • Exercise 1

  • Quiz 1

    3 attempts allowed

  • Lesson 1 Key Takeaways

  • Lesson 2: Choosing and Managing Models

  • The Local Model Landscape

  • Model Families and Their Strengths

  • Benchmark Interpretation

  • Hardware Requirements by Model Size

  • Performance vs Size Tradeoffs

  • Speed Considerations

  • Capability vs Task Complexity

  • Quantization Deep Dive

  • How Quantization Works

  • Quantization Quality Comparison

  • When to Use Higher Quantization

  • Multi-Model Strategies

  • Task-Based Model Selection

  • Model Registry Implementation

  • Using the Model Registry

  • Exercise 2

  • Quiz 2

    3 attempts allowed

  • Lesson 2 Key Takeaways

  • Lesson 3: Prompt Engineering for Agents

  • From Prompts to Specifications

  • The Specification Mindset

  • System Prompt Architecture

  • Structured Prompt Design Patterns

  • Role-Based Prompting

  • Constraint-Based Prompting

  • Step-by-Step Decomposition

  • Guardrails and Safety Instructions

  • The Layered System Prompt

  • Few-Shot and Example-Based Prompting

  • When to Use Few-Shot Prompting

  • Example Implementation

  • Testing and Iterating Prompts

  • The Prompt Test Suite

  • Iteration Best Practices

  • Exercise 3

  • Quiz 3

    3 attempts allowed

  • Lesson 3 Key Takeaways

  • Lesson 4: Structured Outputs and Tool Calling

  • JSON Mode and Schema Enforcement

  • Providing Schema Hints

  • Pydantic Models for Type Safety

  • Function Calling with Ollama

  • Basic Tool Calling

  • How Tool Calling Works

  • Building a Tool Registry

  • Error Recovery for Bad Outputs

  • Retry with Correction Prompt

  • Tool Call Validation

  • Exercise 4

  • Quiz 4

    3 attempts allowed

  • Lesson 4 Key Takeaways

  • Lesson 5: Memory Systems and Context Management

  • The Memory Problem

  • Short-Term Conversation Memory

  • Sliding Window Memory

  • Summarization-Based Memory

  • Long-Term Memory Architectures

  • Episodic Memory

  • Semantic Memory

  • Procedural Memory

  • Context Window Optimization

  • Token Budget Management

  • Selective Context Pruning

  • Implementing a Memory Manager

  • Exercise 5

  • Quiz 5

    3 attempts allowed

  • Lesson 5 Key Takeaways

  • Lesson 6: Retrieval-Augmented Generation and Vector Search

  • Why RAG Is Essential for Agents

  • Embeddings and Vector Spaces

  • How Embeddings Work

  • Using Ollama for Embeddings

  • Embedding Models Available in Ollama

  • Vector Database Options

  • In-Memory Vector Store

  • ChromaDB for Production

  • Document Ingestion Pipelines

  • Text Chunking Strategies

  • Complete Ingestion Pipeline

  • Building a RAG Agent

  • Hybrid Search and Re-Ranking

  • Combining Vector and Keyword Search

  • Re-Ranking with Cross-Encoders

  • Exercise 6

  • Quiz 6

    3 attempts allowed

  • Lesson 6 Key Takeaways

  • Lesson 7: Planning, Reasoning, and Complex Tasks

  • Beyond Single-Turn Responses

  • Chain of Thought and Reasoning

  • Zero-Shot Chain of Thought

  • Structured Reasoning with Explicit Steps

  • The ReAct Pattern

  • ReAct Implementation

  • How ReAct Works

  • Task Decomposition Strategies

  • Hierarchical Task Decomposition

  • Reflection and Self-Correction

  • Exercise 7

  • Quiz 7

    3 attempts allowed

  • Lesson 7 Key Takeaways

  • Lesson 8: Multi-Agent Architectures

  • Why Multiple Agents?

  • Specialization and Roles

  • Researcher Agent

  • Writer Agent

  • Reviewer Agent

  • Communication Patterns

  • Sequential Pipeline

  • Fan-Out / Fan-In

  • Orchestration Strategies

  • Supervisor Pattern

  • Building an Agent Team

  • Exercise 8

  • Quiz 8

    3 attempts allowed

  • Lesson 8 Key Takeaways

  • Lesson 9: Deployment, Security, and Production Practices

  • Packaging Agents as Services

  • Running with Docker

  • Securing Your Agent

  • Input Validation and Sanitization

  • Tool Execution Safety

  • Rate Limiting

  • Observability and Monitoring

  • Structured Logging

  • Performance Metrics

  • Testing Strategies

  • Unit Tests for Infrastructure

  • Integration Tests for Agent Behavior

  • Production Deployment Checklist

  • Exercise 9

  • Quiz 9

    3 attempts allowed

  • Lesson 9 Key Takeaways

  • Lesson 10: Custom Models and Fine-Tuning

  • Custom Models with Modelfile

  • Modelfile Syntax

  • Key Modelfile Directives

  • Advanced Modelfile: Few-Shot Baking

  • Understanding Fine-Tuning

  • When to Fine-Tune vs Prompt Engineer

  • LoRA and QLoRA Basics

  • Creating a Fine-Tuning Dataset

  • Training with ollama

  • Evaluating Fine-Tuned Models

  • Domain-Specific Model Creation

  • The Custom Model Development Process

  • Example: Building a Legal Document Analyzer

  • Exercise 10

  • Quiz 10

    3 attempts allowed

  • Lesson 10 Key Takeaways

  • Lesson 11: Workflows, State Machines, and Orchestration

  • Agents as Workflow Nodes

  • Defining Workflow Steps

  • State Machine Design

  • Implementing an Agent State Machine

  • Async Processing and Concurrency

  • Concurrent Agent Requests

  • Retries, Timeouts, and Circuit Breakers

  • Retry with Exponential Backoff

  • Circuit Breaker Pattern

  • Exercise 11

  • Quiz 11

    3 attempts allowed

  • Lesson 11 Key Takeaways

  • Lesson 12: Advanced RAG Techniques

  • Query Rewriting and Expansion

  • Hypothetical Document Embeddings (HyDE)

  • Query Decomposition

  • Self-Correcting RAG

  • Hierarchical Retrieval

  • Graph-Based Knowledge Retrieval

  • Exercise 12

  • Quiz 12

    3 attempts allowed

  • Lesson 12 Key Takeaways

  • Lesson 13: Building Web Interfaces and Desktop Integration

  • Web Chat Interface

  • Desktop Integration

  • System-Level Agent Tools

  • Real-Time Streaming Dashboard

  • Exercise 13

  • Quiz 13

    3 attempts allowed

  • Lesson 13 Key Takeaways

  • Lesson 14: Performance Optimization and Scaling

  • Inference Performance Optimization

  • Key Performance Factors

  • Measuring Performance

  • Context Length Optimization

  • GPU Memory Management

  • Model Loading Strategies

  • Concurrent Request Handling

  • Request Queue Management

  • Caching Strategies

  • Response Caching

  • Scaling Ollama Deployments

  • Production Configuration Guide

  • Horizontal Scaling

  • Exercise 14

  • Quiz 14

    3 attempts allowed

  • Lesson 14 Key Takeaways

  • Lesson 15: Capstone Project — Building a Production Coding Agent

  • Project Overview: CodePilot

  • Architecture

  • Step 1: Project Setup

  • Step 2: The CodePilot Agent

  • Step 3: Web Interface and API

  • Step 4: Running CodePilot

  • Step 5: Using CodePilot

  • Exercise 15

  • Quiz 15

    3 attempts allowed

  • Lesson 15 Key Takeaways

  • Course Conclusion

  • Where to Go Next

  • Final Principles

The Leanpub 60 Day 100% Happiness Guarantee

Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

See full terms...

Earn $8 on a $10 Purchase, and $16 on a $20 Purchase

We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.

(Yes, some authors have already earned much more than that on Leanpub.)

In fact, authors have earned over $15 million writing, publishing and selling on Leanpub.

Learn more about writing on Leanpub

Free Updates. DRM Free.

If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).

Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.

Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.

Learn more about Leanpub's ebook formats and where to read them

Write and Publish on Leanpub

You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!

Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.

Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.

Learn more about writing on Leanpub