Leanpub Header

Skip to main content

Production AI Agents for Software Engineers

Build reliable AI agents with tool calling, bounded control loops, validation, traces, and production engineering discipline.

The instructor has published 100% of this course.Last updated on 2026-07-18

Stop building fragile AI demos. Learn how to design, test, and operate AI agents like real software systems.

Minimum price

$19.99

$29.99

You pay

Author earns

$

Also available for 1 course credit with a Learner Membership

PDF
EPUB
WEB
About

About

About the Course

Production AI Agents for Software Engineers is a practical course for developers who want to move beyond chatbot demos and build agent systems that can survive real-world use.

You will learn how production-grade agents are structured, how LLM calls fit into normal software architecture, how to design safe tool interfaces, and how to build bounded control loops that stop, recover, and produce useful evidence.

The first release includes modules on agent fundamentals, LLM foundations, tool calling, and agent control loops, plus a simple command-line agent project with quizzes and answers.

This course is for software engineers, backend developers, full-stack developers, DevOps engineers, data engineers, and technical founders who want a practical foundation for building AI agents responsibly.

By the end of the initial modules, you will be able to build a small but real agent that can accept a task, call approved tools, handle errors, stop within defined limits, and return an evidence-based answer.

Share this course

Instructor

About the Instructor

Kevin Languedoc

Kevin Languedoc is a senior data engineer and software developer with deep experience in analytics systems, cloud platforms, and enterprise data architecture. He has designed and delivered end-to-end data solutions across multiple industries and teaches practical, design-focused approaches to modern data engineering.

Material

Course Material

  • 00-preface

  • Production AI Agents for Software Engineers

  • Who This Is For

  • What You Will Build

  • Course Philosophy

  • Technology Choices

  • How To Use This Course

  • Module 1: What Makes an Agent Production-Grade

  • Learning Objectives

  • Chatbot, Workflow, or Agent

  • The Core Agent Loop

  • Production Requirements

  • Failure Modes

  • When Not To Use An Agent

  • Design Exercise

  • Module Summary

  • Module 2: LLM Foundations for Engineers

  • Learning Objectives

  • Messages

  • Instructions Are Not Security Boundaries

  • Structured Outputs

  • Temperature

  • Context Windows

  • Latency and Cost

  • The LLM Adapter

  • Lab: Build A Fake LLM Client

  • Module Summary

  • Module 3: Tool Calling

  • Learning Objectives

  • A Tool Is A Contract

  • Small Tools Beat Giant Tools

  • Tool Input Validation

  • Tool Output Normalization

  • Tool Risk Levels

  • Error Handling

  • Lab: Design Three Tools

  • Module Summary

  • Module 4: Agent Control Loops

  • Learning Objectives

  • The Minimal Loop

  • Stop Conditions

  • Representing Steps

  • Invalid Model Outputs

  • Common Control Patterns

  • Guardrails In The Loop

  • Lab: Add A Step Limit

  • Module Summary

  • Simple Agent Project: Build A Command-Line Engineering Assistant

  • Project Goal

  • Project Files

  • Step 1: Create Sample Data

  • Step 2: Implement Tools

  • Step 3: Create A Fake LLM

  • Step 4: Build The Tool Registry

  • Step 5: Build The Agent Loop

  • Step 6: Script A Successful Run

  • Step 7: Test Failure Behavior

  • Completion Checklist

  • Project Reflection

  • Module 5: State, Memory, and Context

  • Learning Objectives

  • Context, State, and Memory

  • Short-Term State

  • Long-Term Memory

  • The Context Builder

  • Summarization Memory

  • Memory Failure Modes

  • Lab: Add Run State To The Simple Agent

  • Module Summary

  • Module 6: Retrieval-Augmented Agents

  • Learning Objectives

  • Why Agents Need Retrieval

  • Retrieval As A Tool

  • Chunking

  • Embeddings and Vector Search

  • Metadata and Filters

  • Reranking and Context Compression

  • Retrieval Pollution

  • Lab: Add A Knowledge Search Tool

  • Module Summary

  • Module 7: Workflow Agents

  • Learning Objectives

  • Agents Inside Workflows

  • Deterministic First

  • Human Approval Gates

  • Resumability

  • Idempotency

  • Queues and Background Jobs

  • Lab: Design A Ticket Triage Workflow

  • Module Summary

  • Module 8: Multi-Agent Systems Without The Hype

  • Learning Objectives

  • When Multiple Agents Help

  • Use Functions Before Agents

  • Supervisor-Worker Pattern

  • Specialist Agents

  • Handoffs

  • Multi-Agent Failure Modes

  • Lab: Split The Simple Agent Into Roles

  • Module Summary

  • Quizzes

  • Module 1 Quiz

    1 attempt allowed

  • Module 2 Quiz

    1 attempt allowed

  • Module 3 Quiz

    1 attempt allowed

  • Module 4 Quiz

    1 attempt allowed

  • Module 5 Quiz

    1 attempt allowed

  • Module 6 Quiz

    1 attempt allowed

  • Module 7 Quiz

    1 attempt allowed

  • Module 8 Quiz

    1 attempt allowed

  • Module 9 Quiz

    1 attempt allowed

  • Module 10 Quiz

    1 attempt allowed

  • Module 11 Quiz

    1 attempt allowed

  • Module 12 Quiz

    1 attempt allowed

  • Module 13 Quiz

    1 attempt allowed

  • Module 14 Quiz

    1 attempt allowed

  • Module 15 Quiz

    1 attempt allowed

  • Module 16 Quiz

    1 attempt allowed

  • Module 17 Quiz

    1 attempt allowed

  • Module 18 Quiz

    1 attempt allowed

  • Project Quiz

    1 attempt allowed

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