Start free

Mastering Reusable AI Workflows for Real-World Development

Build workflows that compound your productivity

13 lessons2 hr 5 minPlus
Building
Watch lesson 1 freeGet Plus, $219/year
Lesson 1 is free now. The rest comes with Plus.

What you'll gain

Learn how to build, document, and reuse AI-powered workflows that scale across projects. Master the art of creating systematic processes that turn AI from a novelty into a reliable development partner.

Syllabus

13 lessons · 2 hr 5 min

Lets Get Going

1 lesson
1
Auto-Pilot AI Agents at the Right Time
Hey there, my name's Garrison. I'm the founder of Compute SDK. And in this course, we're going to be talking about strategic agents. So you've been using Cloud Code or Cursor, right? Pretty helpful. There's something that you might have noticed, though, and something I've been thinking about. They require your intervention.
6 minFree

Taking It Further

11 lessons
2
Build Your First Strategic Agent
All right, let's build our first strategic agent. By the end of this lesson, you'll have a working code reviewer that can analyze any file and provide specific, actionable feedback. Now, this lesson is just about building the core agent. In the next lesson, we'll connect it to GitHub so it runs automatically on every PR.
12 min
3
Adding GitHub PR Automation To Your First Strategic Agent
We're taking the PR agent and connecting it to GitHub Actions so it runs automatically whenever someone creates a PR. You'll see how to transform this local tool into a strategic automation that works 24/7.
14 min
4
CodeRabbit Setup and Functionality
So you've built your own code review agent, and you've seen how it works. Now let's set up Code Rabbit, an enterprise-grade professional code review assistant. We're going to see how it looks in practice. I'm going to walk through the real setup process, show you the actual interface, and we'll see the results. Let's dive in.
10 min
5
Build Your Second Strategic Agent: Bug Fixer
You know that feeling on a Friday evening when you're staring at your computer and you're thinking, how am I still here? I pushed to production a few hours ago and for some reason I'm staring at stack traces still. That's right. You pushed to production and now you have a ginormous bug in your hand. Your boss is mad at you.
12 min
6
Adding Github Actions Automation to Your Bug Fixer
6 min
7
Connecting Your Bug Fixer to Production Error Monitoring
So you've built a bug fixer that handles test failures and development issues. What about production errors? What about the complex debugging when real users hit real problems with distributed systems, logs, and traces? Today, we're going to be looking at SentrySeer.
14 min
8
Build Your Third Strategic Agent: Documentation Writer
Today we're building our third strategic agent. Our third strategic agent is a documentation writer. Let's talk about documentation for a second. Docs are frequently a thing that we like to forget about. You'll write a particular feature, and then you'll think to yourself, well, let's get this into production, and you'll wait.
8 min
9
Automatic API Documentation with GitHub Actions
So you've got a documentation writer that can analyze code and generate comprehensive docs. But if you have to remember to run it every time, you can change an endpoint and forget. In this lesson, we're connecting your documentation writer to GitHub Actions so it runs automatically whenever you modify API routes.
8 min
10
Agent Configuration Systems
Learn how to leverage **AI agents** to automate complex tasks. ### What are AI agents? AI agents are autonomous systems that can: - Read and understand your codebase - Execute multi-step plans - Run commands and iterate on results In this lesson, you'll see agents in action and learn how to configure them for your workflow.
10 min
11
Custom Prompts and Templates
Here we're looking at our solid configuration system that lets teams customize their agents. But here's the thing. The real power comes from controlling exactly how your agent thinks. Today we're building a custom prompt system that lets you completely control the context of your agent.
10 min
12
Cost Controls and GitHub Issue Tracking
So you've got configurable agents with custom prompts that work exactly how your team works. But here's the reality check. AI isn't free. Today we're adding smart cost controls that integrate directly with GitHub issues. Your team gets budget alerts and usage reports right in your existing workflow. No separate tools to check.
9 min

Lets Close Off

1 lesson
13
What You've Built: Strategic Agent Mastery
All right, let's step back and see what you've accomplished. When you started this course, you probably thought about LLMs as something you chat with when you need help, like a cloud or a chat GPT, an interface kind of like this, maybe.
6 min

Certificate

Preview
unlearn
Certificate of completion
Your name
Mastering Reusable AI Workflows for Real-World Development

Shareable, with a public verification link.

Finish all 13 lessons to claim it.

Access

It's part of Plus. Lesson 1 is free to watch for everyone, no account needed.

Every lesson of every course, the full notes, transcripts and prompts, and the Unlearn-built tools. Blog posts and the tools that are public on GitHub stay free for everyone.

Yes. Finish all 13 lessons to earn the Mastering Reusable AI Workflows for Real-World Development certificate.

Yes. Team plans can assign this course, or a whole role, and follow progress in Team.

Next step

More in Building
Build Features with an AI Agent
Workflow · 12 lessons · 1 hr 38 min
Go to the next step