[go: up one dir, main page]
Developer education for the AI era

Be the most dangerous developer in the room.

AI solved the easy half of your job, now what?

Seats Full

Opening soon. Join the waitlist to lock in the lowest price.

In the meantime, enjoy receiving practical AI workflows and dev insights.

Already a customer? Sign in →
From the team that trained 2,000,000+ developers at

Using AI and using it well are not the same thing

You're shipping faster than ever. AI writes the boilerplate, scaffolds the features, and handles the patterns you used to type out by hand.

It's not just you, 84% of developers use AI tools regularly now, and the ones who pushed early are getting more done with less effort.

But AI doesn't level the playing field. It tilts it.

The developer who knows how to feed AI the right context and build systems around it now has a brutal advantage, because AI amplifies whatever you bring to it.

Strong engineering instincts scale.

Weak ones scale too...

but in the wrong direction.

There's a growing gap between developers who use AI and developers who've built the systems to make it work at their level.

With a system

Ships a full feature in a day with AI handling the implementation

Without a system

Same tools, half the time fighting hallucinations and re-prompting from scratch

  • No context files that teach AI your codebase
  • No guardrails that catch mistakes before they ship
  • No proper rules, hooks, or MCPs that make the output production-ready

The tools are there, you just haven't built the system around them yet.

This gap isn't new. Every time software added a new layer of abstraction, the same thing happened.

Every abstraction in software was once someone else's job

Assembly gave way to compilers, compilers gave way to frameworks. Each layer automated work that developers used to do by hand, and every time, the same argument started about whether the old skills still mattered.

They did. But the job changed around them, and the developers who figured out each new layer fast became the ones everyone else relied on.

AI is the current layer. It won't be the last.

But this one is different. Previous layers automated tedious work. AI automates the part that felt like your job. The output looks like something a developer wrote.

That changes what you need to be good at, and what you can finally let go of.

Worth unlearning

  • The reflex to write every character yourself
  • Prompting from scratch instead of building systems that compound
  • Measuring value by lines of code, not decisions made
  • Prompting without leveraging your technical edge

Never unlearn

  • Knowing when to trust AI and when to take over
  • Architecture decisions that hold up when AI writes the code
  • Knowing that what we feed AI matters more than how we prompt it
  • How the system fits together, what runs where, what breaks

That all sounds reasonable on paper. But it hits different when you see it in your own code.

Let's play a game

Here's a simple permissions check AI generated. Six lines. It compiles, it passes linting, and it looks production-ready. See what you catch.

permissions.js
1// permissions.js
2async function getUserPermissions(userId) {
3 const user = await db.query(`SELECT * FROM users WHERE id = ${userId}`);
4 const permissions = user.roles.flatMap(role => role.permissions);
5 return [...new Set(permissions)];
6}

Tap the underlined code to see why each one matters.

Six lines of code, three issues. A real PR has hundreds of decisions just like these.

Every one of them is context the model didn't have. You do.

And catching bad code is just the beginning. The same kind of judgment matters when you're scoping features, steering AI through an implementation, or building the guardrails that prevent these issues in the first place.

Join the waitlist

You learn something actionable every 15 minutes you spend here.

Went through the Unlearn material and it's easily the best I've seen on architectural thinking in an AI workflow. Really good stuff.

Filip Rakowski / Co-founder & CTO, Alokai

That's why we built unlearn

Most AI education teaches you how to use a tool.

We teach you how to become the developer nobody wants to compete with.

  • Makes the architectural calls AI will never be qualified to make
  • Ships in a day what used to take a sprint
  • Builds systems that make every output production-grade

Unlearn is a living platform, not a course you finish and forget. Workflows, courses, workshops, and tools that evolve together, shaped by what 30,000 developers told us and built to keep up with how fast AI moves.

AI changes fast. You can have a system that changes with it, or you can keep figuring it out alone.

The skills that make you essential

The tools that make you resourceful

Tools you plug into your editor today, updated the same week a new model ships.

Designed to work with your stack and tools

Frameworks & Technologies

TypeScriptTypeScript
ReactReact
Next.jsNext.js
Vue.jsVue
NuxtNuxt
Node.jsNode.js
PythonPython
AngularAngular
SvelteSvelte
LaravelLaravel
Tailwind CSSTailwind
DockerDocker

AI Coding Tools

GitHub Copilot
Claude
Cursor
OpenRouter
Coder
StackBlitz
JetBrains
CodeRabbit
v0
Windsurf
Gitpod
Google Gemini
Zed Industries
LangChain
Perplexity

Your full build cycle, covered

We're launching with 8 core workflows, each one built for how the job actually works now that AI writes the code.

You watch a short lesson, grab a prompt or an MCP server or a skill file, and use it on your actual project that same day. Fifteen minutes from learning something to shipping with it.

Spec a Product Before AI Builds It

AI knocked down the walls. You can build a SaaS, ship a mobile app, or automate an entire backend without needing a full team behind you. But the developers who actually finish what they start are the ones who plan before they prompt. So you set constraints, define what AI is NOT allowed to build, and use AI itself to poke holes in your plan before writing a single line of code.

21 prompts10 templates2 skills1 checklist
10 lessons34 resources

From vague idea to actionable product plan

  1. Why Planning Beats Vibe Coding (4m)
  2. Turn a Vague Idea Into a Structured Spec (6m)
  3. Shaping the Specification (2m)
  4. Give AI Technical Constraints from Day One (3m)
  5. Tell AI What It's Not Allowed to Build (2m)
  6. Use AI Mockups to Expose Gaps in Your Spec (2m)
  7. Have AI Poke Holes in Your Plan (2m)
  8. What Might We Have Missed? (2m)
  9. From Spec to Features (2m)
  10. Scaffolding the Boilerplate (5m)

Design a Feature AI Can Execute Without Guessing

AI is fast at building but terrible at deciding what to build, so the precision of your instructions determines everything. You break a feature down into tasks so clear that AI has nothing to interpret, with acceptance criteria it actually follows and a sequence that keeps scope from creeping into places you never intended.

11 templates10 prompts1 checklist
7 lessons22 resources

From specification to feature-ready plan

  1. From Specification to Feature Plan (3m)
  2. Decompose Features Into Tasks AI Can Handle (4m)
  3. Write Acceptance Criteria AI Will Actually Follow (3m)
  4. Estimate Effort and Flag Risks Early (4m)
  5. Sequence Tasks for Incremental Delivery (3m)
  6. Create the Implementation Checklist (4m)
  7. Validate the Plan Before Handing Off to AI (3m)

Build Features with an AI Agent

Most developers hand the agent a prompt and hope it figures things out. The ones shipping clean code every day have a loop instead. Feed context before you ask, let the agent take a first pass, review without rewriting everything, then handle edge cases and write tests together before going from branch to production.

1 checklist1 prompt1 guide
12 lessons3 resources

From plan to production-ready code with AI agents

  1. The AI Implementation Loop (5m)
  2. Set Up Your Agent Environment (8m)
  3. Feed Context Before You Prompt (6m)
  4. First Pass: Let the Agent Build (10m)
  5. Review What the Agent Wrote (8m)
  6. Iterate: Refine Without Starting Over (7m)
  7. Handle Edge Cases and Error Paths (10m)
  8. Write Tests With the Agent (12m)
  9. Integration and Regression Checks (8m)
  10. Clean Up Before Commit (6m)
  11. Document What Changed and Why (5m)
  12. Ship It: From Branch to Production (10m)
Reviewing AI-Written Code workflow illustration

Reviewing AI-Written Code

AI-generated code looks clean, passes lint, passes tests, and then breaks in production because nobody traced through the logic that only fails under real conditions. This is where you build the review instincts of a senior engineer, catching the patterns that no linter or test suite will flag for you.

April
Merging and Deploying workflow illustration

Merging and Deploying

The tests pass and the PR looks right, but there's still that feeling in your gut because you didn't write every line yourself. The gap between "it looks correct" and "I'd bet production on it" is real, and closing it takes a deploy process built specifically for code you directed but didn't type.

April
Debugging and Performance workflow illustration

Debugging and Performance

Something breaks at 2am and half the codebase was AI-generated, which means you can't grep your own memory for context that was never yours. So you turn AI into your debugging partner instead, tracing through its own output, isolating the root cause, and fixing it without making things worse.

April
Refactoring with an AI Agent workflow illustration

Refactoring with an AI Agent

Refactoring is where AI gets dangerous, because one wrong instruction and the agent rewrites half your codebase with changes nobody asked for. You keep refactors incremental and test-covered at every step, so you actually improve architecture instead of gambling on whatever the agent decides to touch.

April
Getting Up to Speed on Any Codebase workflow illustration

Getting Up to Speed on Any Codebase

New job, new repo, 200k lines of code and zero documentation to go with it. AI can map the whole thing faster than any onboarding doc ever could, but only if you know how to ask the right questions. You turn it into a codebase guide that builds your mental model, surfaces the entry points, and gets you making safe changes in days instead of weeks.

April

Every workflow ships with

Lessons
Exercises
Videos
PromptsMCP ServersAI Skills
Join the waitlist

These eight are the starting line. We're building in parallel to cover more of the AI spectrum, and the developer stays at the center of all of it.

Five courses, and they're all yours from day one

We've prepared 5 full courses alongside the workflows. Which tools to actually commit to, how to hand off work to AI without losing control, and how to trust your own review when the code isn't yours.

The Future Proof Dev course illustration
AI FUNDAMENTALS1h 7m

The Future Proof Dev

Most developers installed Copilot, accepted a few suggestions, and called it a day. But AI coding tools go way deeper than autocomplete, and the gap between using them casually and using them well is where most of the value lives. You build a real mental model of what these tools can and can't do, so you stop guessing and start directing.

1Introduction to AI for Web Developers3m
2Conclusion2m
3What is AI (for Developers)?4m
4A Gentle Onboarding to AI in Your Everyday Workflow4m
5More Examples of Using AI for Common Development Tasks10m
6Powering Up Your IDE with AI8m
7What is Context?3m
8Targeted Quick Edits with AI2m
9AI Agents That Write Code, Run Commands, and More13m
10Putting Agents to Work in Parallel (Asynchronous Background Agents)9m
11High Level Overview of Other Specialized AI Development Tools3m
Mastering Reusable AI Workflows course illustration
AI WORKFLOWS2h 5m

Mastering Reusable AI Workflows

You figured out a good prompting pattern for code review. Then you did it again for bug fixing. Then documentation. At some point you realize you're rebuilding the same process from scratch every time. This course teaches you to turn those patterns into reusable agents that run on autopilot, connected to GitHub Actions and your actual error monitoring.

1Auto-Pilot AI Agents at the Right Time6m
2Build Your First Strategic Agent11m
3Adding GitHub Actions Automation to Your Bug Fixer6m
4Connecting Your Bug Fixer to Production Error Monitoring13m
5Build Your Third Strategic Agent - Documentation Writer8m
6Automatic API Documentation with GitHub Actions7m
7Agent Configuration Systems9m
8Custom Prompts and Templates9m
9Cost Controls and GitHub Issue Tracking9m
10What You've Built - Strategic Agent Mastery6m
11CodeRabbit Setup and Functionality10m
12Build Your Second Strategic Agent - Bug Fixer11m
Optimizing Productivity with AI Tools and Agents course illustration
AI PRODUCTIVITY2h 22m

Optimizing Productivity with AI Tools and Agents

There are dozens of AI coding tools and every week someone launches a new one. The real question isn't which tool is best, it's which combination actually fits how you work. You learn to pick the right editor, the right agent, configure rule files and MCP servers, run agents in parallel, and build a personal setup that compounds over time instead of fighting you.

1Understanding AI Productivity1m
2Keeping up with the AI landscape14m
3Choosing the Right AI Code Editor5m
4Choosing the Right AI Agent: AI Meets CLI11m
5Rule files21m
6Using MCP to Extend Your Agents8m
7Building a Custom MCP Server Intro (Customer Support Example)7m
8Sub-Agent11m
9Parallel Agents13m
10AI Development Best Practices15m
11Agent Workflow7m
12Conclusion1m
13Building a Custom MCP Server (Walkthrough)22m
RAG for Real-World AI Applications course illustration
AI ENGINEERING4h 20m

RAG for Real-World AI Applications

Every developer wants to connect AI to their own data, but most RAG tutorials stop at "put your docs in a vector database and query them". The real work is chunking strategies, embedding model selection, reranking, evaluation, and knowing when your pipeline is actually returning good results versus confident garbage. You build a production RAG system from scratch and learn to measure whether it works.

1Intro to Real World RAG3m
2Real World RAG Use-Cases from Top Companies4m
3How RAG Works - A High Level Overview5m
4Project Setup and Vibe Coding the Chat UI13m
5Gather and Clean Documents with Llama Parse10m
6Open Source Alternatives to Llama Parse6m
7All About Chunking for RAG4m
8Chunk the MDN Docs for our Project16m
9Compare Embedding Models for RAG5m
10Compare Vector Databases for RAG3m
11Use AI Agent to Setup a Postgres Database and Drizzle12m
12Update the Database Schema for Documents and Chunks14m
13Criteria for Evaluating RAG Results5m
14Get Started with PromptFoo for RAG Evals10m
15Evaluate RAG Context Recall - Retrieval Effectiveness6m
16What is Cosine Similarity and Top-K in RAG6m
17Augment Generative AI Input with Related Content16m
18Evaluate RAG Context Adherence-Faithfulness10m
19An Eval to Check for Linked Sources and Some Refactoring6m
20How to Implement Contextual Embeddings for RAG6m
21How to Implement BM25 for RAG16m
22An Overview of Strategies to Improve RAG Results5m
23How to Implement Reranking for RAG5m
24Course Conclusion1m
25Use AI Agent to Create Database Seed to Store Documents9m
26Retrieve Semantically Related Content5m
27Create Embeddings and Store in a Vector Database14m
28Documenting RAG App Scripts and Service Functionality8m
29Hook Up the RAG Pipeline to the Web App13m
30Streaming The RAG Response With the AI-SDK12m
AI for UI Design and Automated Testing course illustration
AI DESIGN2h 40m

AI for UI Design and Automated Testing

You can ask AI to build a component, but what you get back usually looks like every other AI-generated interface on the internet. This course is about using AI as a real design partner, from generating image assets and brainstorming layouts to building animated hero sections and creating spritesheets, all while keeping your brand intact and the code maintainable.

1AI for UI and Testing Course Intro
2Don't Always Start From Scratch, Use a Template
3Setup the Project Design System to Work for Our Brand
4Focus on the Details and Aura.build
5Scaffold Home Page, Refine Orange Color, and Solidify Dark Mode
6Use Image Generators to Brainstorm Designs
7Generate Image Assets with Gemini Flash (Nano Banana) Without a Watermark
8Give Cursor (Or Any Agent) Image Generation Capabilities
9Go from Image to Code Accurately with the Browser Tool
10Use ImageMagick or Sharp To Remove Generated Image Backgrounds
11Create Engaging Heroes with Video Backgrounds
12Create an Interactive Animated Hero Section with AI
13Repurpose UI Ideas to Create a Reveal Video Micro Interaction
14Generate Spritesheets for Organic Re-usable and On-Brand Elements
15Use AI to Design a Layout Based on a Screenshot

New courses and workflows ship every week.

Your path, not someone else's

Answer a few questions about how you work. We'll show you exactly what Unlearn looks like for you.

Your primary stack?

AI coding tool you use?

Biggest challenge right now?

Your recommended path

ReactReact / Next.jsClaudeClaude Code
The bottleneck isn't Claude. It's the workflow around it.

Claude Code is one of the highest-leverage tools in React / Next.js development right now. This path tightens the loop — from MCP-powered planning through automated deployment checks — so every session compounds.

Your workflow path

Planning

Use CLAUDE.md and slash commands to write specs Claude executes reliably.

Executing Features

Chain Claude commands in small, safe PRs with test coverage at each step.

Merging & Deploying

Use MCP servers to validate CI and automate pre-merge checks.

First session: ~18 min
I've mass-ignored everything out there on AI for developers because it all looks great in a demo and falls apart on anything real. But Unlearn actually changed how I build things.

Kostas Maniatis / Full Stack Developer at Flexpedia

Become dangerous

AI raised the bar.

It's time to sharpen your technical edge and make AI your multiplier

Seats Full.

1,000+ early members are already inside. Join the waitlist to access the next opening.

Drop your email and we will notify you the moment doors open.

→Every workflow, course, and tool we ship is yours
→8 workflows covering your full development lifecycle
→5 courses with full access from day one
→New content added every week
→MCP servers and skill files, ready to install
→The Unlearn Podcast
→Access to Discord community and live events
→Exclusive onboarding workshop
→Your input shapes what we build next
→First access to every platform beta feature
→Early access badge, permanent and visible
→Team management and seat administration
→Custom workflow builder for your stack and
conventions
→Shared context files, guardrails, and skill files across the team
→Volume discounts that grow with every seat
→Priority onboarding and dedicated support
→Centralised billing
→Customisable invoice
For teams

Get your whole team on one system, not six different ways of using AI.

  • Team management and seat administration
  • Custom workflow builder for your stack and
    conventions
  • Shared context files, guardrails, and skill files across the team
  • Volume discounts that grow with every seat
  • Priority onboarding and dedicated support
  • Centralised billing
  • Customisable invoice

Want to reserve team access or need a tailored training track? Contact us

You already know AI isn't the hard part

Built for you if
  • →You ship production code and you're responsible for what goes out the door
  • →You've outgrown random tips and tricks and want a system you can rely on
  • →You care about understanding what you ship, not just shipping it
Not for you if
  • ×You want to hand everything to AI and approve whatever comes back
  • ×You're not building production software
  • ×You think AI replaces the need to be a good developer

Not for everyone. That's the point.

We can make you two promises

Your price. Permanently.

This is the lowest price Unlearn will ever be sold at. As an early access member, your price stays for as long as you do.

It's an early access rate, not a discount.

We keep shipping, you keep getting it

New workflows, updated prompts, and new MCP servers ship every week. The subscription covers everything we'll ever build.

You pay once a year. We ship every week. That's the deal.

Once you're in

  1. 1

    We email you when access opens

    You'll hear from us about a day after you check out, or when this sale closes. Every course, workflow, and tool we ship is yours from the start.

  2. 2

    Take the 30-second path quiz

    We show you which workflows matter for how you work.

  3. 3

    Start your first workflow

    Most people finish module 1 in 15 minutes.

Alex Garrett-Smith
Alex Garrett-Smith

Technical Education Lead

@BitterBrains

Alex started recording screencasts in 2009 while he was still learning to code.

He built Codecourse into a 300,000-subscriber YouTube channel while holding down a full-time dev job. What started as screencasts grew into a full learning platform, then got acquired in 2025.

Then he joined the BitterBrains team to take on a bigger challenge, figuring out how developers actually work with AI. He now leads the curriculum and judgment frameworks behind unlearn.

2009 → now

Sixteen years teaching developers how to build. Now writing the playbook for what comes next

Built by the team behind
Vue SchoolAIDDCertificates.devFrontendNation
Creators of Certification Programs
React CertificationAngular CertificationLaravel CertificationOfficial Nuxt CertificationJavaScript Certification

0+

Developers trained

Our students work at

Still here? Good.

Our founding members are already building. We will reopen soon.

Join our newsletter to get notified the moment we reopen. Until then, receive practical AI workflows, dev insights, and free resources.

No spam. Useful stuff only.

Got questions?

On March 31 we opened 500 founding seats, and they sold out in under 8 hours. We weren't planning a second round, but the demand caught us off guard, so we opened 400 more. Those sold out too. Round 3 added 300 final seats. All three rounds are now closed. Over 1,000 developers from companies like Microsoft, Google, Amazon, Adobe, and Bloomberg locked in early access pricing before we'd sent a single launch email to our full network.
When we opened early access, we made a commitment to the developers who joined first. They trusted us before the platform was live, and in return, we promised to give them our full attention and involve them in shaping what we build next. Closing enrollment allows us to focus on delivering on that promise. We’re actively building workflows, responding to feedback, and refining the experience to make sure it truly improves how developers work. Once we’ve incorporated this feedback, we’ll reopen for the next wave.
Soon. We don’t have a fixed date yet, as it depends on how quickly we refine the product with our founding members. Join the waitlist and we’ll notify you the moment we reopen.
During early access, developers who secured one of the founding seats across the three rounds received full access to everything we offer, including all current and future workflows, courses, MCP servers, agent skill files, and community features. Everything we build from here continues to be included in their subscription, with no additional cost. Their price is locked in permanently. They also have the opportunity to shape the product during this phase by sharing feedback that directly influences what we build next. What’s included in the subscription will remain the same for future openings. The difference is that early members secured the lowest possible price and a chance to contribute to the product as it evolves.
Inside Unlearn, you’ll find a complete system for building with AI as a developer. At the core is our flagship 8-phase workflow that takes you from idea to production. Each phase includes step-by-step lessons, prompts, MCP server integrations, and AI skill files you can use directly in your editor. You’ll also get five in-depth AI courses covering the fundamentals and specializations behind the workflows, including reusable workflows, agents, RAG, UI, and testing. Everything is designed to be used on real projects. We ship new content every week, and it all becomes part of the platform as it grows.
Yes. The core workflows and judgment frameworks apply to any stack and any AI tool. But we go deeper than that. We build stack-specific tutorials and examples for frameworks like React, Vue, Laravel, Angular, and more. If you work with it, we cover it or we will. The same goes for AI tools. Whether you use Claude, Cursor, Copilot, or something else, you get tool-specific guidance on top of the principles that work everywhere.
No. Courses are one piece of it. But if all you needed was another video library, you'd have solved this problem already. Unlearn is built around workflows, the things you actually need to do, not technologies you need to learn. Every workflow has lessons, short videos, exercises, ready to use templates, AI prompts you can paste directly, MCP servers you can connect to your editor, and agent skill files you can install. Learn the principle, grab the tool, and use it today.
In a survey of 3,080 developers, 44% rated themselves 'Average' at judging AI output. They ship faster, but they second-guess more. Using AI and trusting your review of AI output are two different things. If you're already using AI heavily, you'll get more from this than someone just starting. In a controlled trial by METR, experienced open-source developers using AI were 19% slower than without it, but believed they were 20% faster. The gap between using AI and using it well is bigger than most people think.
MCP servers are integration tools that let Unlearn workflows run directly inside Claude, Cursor, or your AI tool. No copy-pasting, no context switching. You learn a review pattern and the MCP server applies it the next time you open a PR. Skill files work the same way for AI agents. Install one, and your agent follows the patterns you learned automatically. These aren't extras. They're core to how Unlearn works.
You get a dashboard to manage members, track progress, and control access. Add or remove team members anytime. Everyone shares the same context files, skill files, and guardrails. If you want to reserve team access before sales reopen, email team@unlearn.dev and we'll work out the details.
Full refund within 30 days. No form. No retention call. No "tell us why". If Unlearn doesn't noticeably change how you work, you shouldn't pay for it. We're not asking you to trust a landing page. We're asking you to try Unlearn. If it doesn't feel worth it, email team@unlearn.dev and we'll issue a full refund.
Email team@unlearn.dev. We read every message and aim to reply the same day.
What they say

“Developers are cooked.”

What matters
Bebettertodaythanyesterday.