Build Features with an AI Agent
From plan to production-ready code with AI agents
12 lessons1 hr 38 minFree Oct 10 to 11
Lesson 1 is free now. Free Oct 10 to 11 (opens Fri 22:00 CEST) with a free account.
What's inside
- AI pair programming best practices
- Testing strategies with AI assistance
- What you'll build in this workflow
What you'll gain
Direct an AI agent through the full build cycle without losing control of what gets shipped.
- Following your technical plan, you'll set up AI-assisted development, implement features with AI pair programming, write tests, review code, and deploy — building a repeatable shipping process.
When to use it
- Ready to implement from a technical plan
- Want to learn AI-assisted coding patterns
- Need to ship features with fewer defects
You'll reach for it: Every implementation cycle
What you leave with
1
Checklist
1
Prompt
1
Guide
Syllabus
12 lessons · 1 hr 38 min1
Guardrails Before AI Generated Code
In this lesson, you'll set up guardrails in your boilerplate before letting AI start building features, ensuring it sticks to your conventions.
5 minFree
2Navigating Your AI Agent
Learn the essential commands and interaction patterns for working with AI coding agents. Master the interface so you can direct the agent efficiently throughout your workflow.
18 min
3Start with AGENTS.md
In this lesson, you'll learn about agent files — files loaded into an agent's context before it works on a task, giving you an opportunity to provide guidance every time.
5 min
4Implementing Tests Before AI Generated Code
In this lesson, you'll learn why writing tests before implementation with AI produces better results than generating tests after the fact.
12 min
5Using Hooks as Part of Our Workflow
In this lesson, you'll learn how to use hooks to automatically run your guardrails, so neither you nor your AI agents forget them.
9 min
6Reviewing and Refining Agent Decisions
In this lesson, you'll learn to regularly review, add, and refine guardrails based on what you observe during implementation.
6 min
7Rapid Review and Refine Cycle
In this lesson, you'll develop a fast feedback loop with your AI agent for iterative code improvement.
5 min
8Planning Inside Your Agent
In this lesson, you'll take feature planning entirely into your agent, discussing trade-offs and mitigating downsides to keep work focused and reviewable.
11 min
9Small, Focused Branches
In this lesson, you'll learn why smaller, focused branches and pull requests are essential when working with AI agents that generate large amounts of code.
10 min
10Picking up Where You Left Off
In this lesson, you'll learn strategies for resuming AI agent sessions after breaks, so you don't lose plans and context between sessions.
8 min
11Local Code Reviews without Humans
In this lesson, you'll learn to hand off your code for review to another AI agent as an additional guardrail before merging.
7 min
12Using Checklists
In this lesson, you'll use structured checklists to guide your AI agent through multi-step tasks, keeping complex features on track.
3 min
Access
Yes, Oct 10 to 11. It's one of the 6 courses free to watch with a free account that weekend (opens Fri 22:00 CEST).
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.
It shows as Completed on your profile and counts toward its role. Finishing every step of a role earns the role certificate.
Yes. Team plans can assign this course, or a whole role, and follow progress in Team.
Next step
Next in Product Engineer
Reviewing AI-Written Code
Workflow · 12 lessons · 1 hr 34 min