Wesley Morris, the host of the culture podcast “Cannonball,” joins us in April to chat with teenagers all about podcasting. Post your comments and questions for him by April 15.
Why the Future of Learning Starts with Building
Coding has always served two purposes: the intrinsic drive to build something, and the practical path to a lucrative career. Even the most passionate code aficionados don’t dream of variables or syntax — they want to make a website, a tool, a game. For years, the career upside was impossible to ignore. You could land a stable SWE job, bootstrap your own app, or join a buzzy startup as a first hire.
Generative AI flipped the script. AI now handles the repetitive tasks that used to define entry-level developer roles. At the same time, the barrier to entry for coding and building is lower than ever — you can spin up a working prototype with just an idea and a natural language prompt.
This shift hasn’t eliminated the desire to code, but it’s changed what and who coding is for. If you’re not learning to land a junior dev role, you’re learning to build the thing you’ve been imagining, to add a technical skill to your existing career, or to understand the tools you’re already using at work. And here’s the catch: those goals all require understanding your code, not just having code that works.
At Codecademy, all of these changes excite us about the future of learning to code. We’re introducing the AI Builder, a new project-based learning tool that flips the script by teaching you how to work with AI-generated code from the start. Our approach brings together the immediacy of modern AI tools and the rigor of real instructional design.
Why we created the AI Builder
AI’s speed and efficiency often come with a tradeoff; you can get working code immediately, but you don’t really know what it’s giving you or why it’s built a certain way. Developers use the term “vibe coding” to describe this phenomenon — it’s fast, fun, but shallow; great for demos, less great for long-term skill-building.
If your goal is to understand what you’re building, generic AI output alone won’t get you there. And the more you push these tools into real-world complexity, “the harder it is for them to give you exactly what you want,” says Zoe Bachman, Head of Learning at Codecademy.
With the AI Builder you get an education along with the AI output. In the workspace, you can toggle between two tabs: Build, where you work directly with a project and can modify and change code in real time; and Learn, where you get a personalized learning roadmap that’s based on your project.
“We pair the experience of having a working app with a learning path that allows you to reverse engineer how it’s built, so you can deeply understand it and modify it confidently,” Zoe says. We’re calling our hybrid approach to learning-driven development “vibe learning” — it’s powered by AI guidance but rooted in learning science.
Build first; learn continuously
With AI Builder, you start with what you want to do: build the thing in your head. Whether that’s a habit tracker, a portfolio site, or the seed of a bigger idea, you don’t need to have prior coding knowledge to learn and build with the AI Builder. In other words, there are no pre-requisites for creation.
You create a prototype by typing what you’d like to create in natural language. The AI chatbot will ask a few clarifying questions about your needs and overall goal before generating the project. Once the project is created, you can use the chat function to continue describing what you want. (You’re also welcome to go right into the code and start making changes if you already know your way around!)
“It was fun to build something so quickly and be able to see the code and a learning plan for it,” says Grace Krishna, a Code Crew member who beta tested the AI Builder.
When you need clarity on what’s going on behind the scenes in your code, or you hit a wall with AI, that’s a great time to flip over to the Learn tab.
We’re calling our hybrid approach to learning-driven development ‘vibe learning’ — it’s powered by AI guidance but rooted in learning science.
Your project becomes the curriculum
Rather than teaching concepts in the abstract and hoping learners translate them later, AI Builder removes that translation tax entirely. “We’re showing you specifically your code from your project and helping you understand it,” Zoe says.
To build that personalized curriculum, the AI Builder breaks your project’s code into clear milestones and tasks. For each task, it generates an interactive learning loop, which is an activity designed to help you form a mental model of what your specific code is doing.
These loops help you understand the logic behind each part of your project, so you can confidently apply the same thinking to other sections, or even future projects. This approach also ensures everything you learn is directly relevant to what you’re making — so you don’t have to guess when you’ll ever use this.
Why this is vibe learning (not vibe coding)
A key misconception about AI‑assisted development is that it makes learning superficial. AI Builder challenges that by grounding the entire experience in learning science rather than simple code generation. Our entire system is intentionally designed for you to retain knowledge. So, while it might not feel like you’re taking a course, you’re absorbing key concepts just by interacting with AI-generated code.
A Socratic AI, not an answer-spitting chatbot
Our educational AI chatbot is designed to guide you toward an answer through an in-depth questioning approach that’s based on the Socratic method of teaching. Instead of spitting out shortcuts or answers like AI typically does, you get strategic nudges, hints, and questions that build durable mental models.
Research on AI in education shows that just providing an answer makes it harder for learners to retain the information on their own. Zoe compares the Socratic AI to “a personalized tutor, facilitating you acquiring more knowledge, so you’re not totally left on your own.” Our method encourages you to think critically so you really grasp the concepts and can continue to use them in the real world.
Learning loops with real instructional design
Behind the scenes, every learning loop in the Learn tab is built on proven frameworks like inductive learning and the 5E model, a popular STEM teaching framework that’s shorthand for engage, explore, explain, elaborate, and evaluate.
You’ll notice that the questions and exercises in the Learn tab feel different than the rest of our courses and paths, and that’s intentional. “The learning loops are designed very well — they get you there inductively,” Zoe says. They’re exploratory without being overwhelming, and evaluative without feeling like tests.
Negar Vahid, a beta tester for the AI Builder appreciated the AI’s interactive question format. “The question-based learning feels engaging, and the starter project it builds is simple but useful,” she says.
This structure ensures you don’t develop the wrong mental models — a known risk in fully constructivist or student-centered environments — while still giving you the freedom to explore.
Why learn when AI can build?
There are some projects that are well-suited for simply vibe coding, like making a personal HTML website or a single-use script to automate a one-time task. Tools like Lovable and v0 are suited exactly for these types of projects.
The longer your code needs to live, and the more complex your project becomes, the more you need to actually understand what you’re building. Joe Holmes, Codecademy Curriculum Developer in the AI and machine learning domain, uses the term “ignorance debt” to describe what happens when you don’t:
“It’s like tech debt squared. It’s much, much worse,” Joe says. “You don’t know what kind of code is coming out. You just are only looking at: Does this kind of generally appear to be what I asked for? You don’t know if there are security flaws. You don’t know if there are performance flaws. You don’t know if you’re leaking sensitive information. You don’t know how to fix anything.”
The tipping point comes down to two factors: complexity and time. If you’re developing software professionally, you’re legally responsible for the code you output. If you’re building something that will serve actual users, you need to be accountable for security, performance, and maintainability. And if your project will need updates or fixes over time (which most do) understanding your codebase becomes essential, not optional.
The good news? Learning doesn’t have to feel like eating your vegetables. “Kids hate veggies and broccoli because we don’t cook it well enough to make it tasty when we first introduce it to them,” says Nhi Pham, Codecademy Curriculum Developer. The same is true for teaching AI: “If you do it well, you’re inspiring people to have these very hygienic practices when working with AI,” she says.
That’s exactly what AI Builder is designed to do — make learning feel as immediate and rewarding as building, so you develop good habits from the start rather than building a lifelong aversion to understanding your own code.
Get started with the AI Builder
AI isn’t a replacement for learning, it’s a tool — and a powerful one when it comes to education. Our new AI Builder allows for “just‑in‑time learning that’s highly personalized,” Zoe says. Even the best teachers or bootcamps can’t deliver that for every learner, on every project, instantly. Perhaps the most exciting vision is how AI changes what a learning environment can be.
Zoe described it beautifully: “I imagine the AI Builder as a workspace… like having all your resources around you and an AI tutor in the background.”
That’s the shift: from learning before you build to learning while you build. We can’t wait to see what you create.
Why the Future of Learning Starts with Building
Coding has always served two purposes: the intrinsic drive to build something, and the practical path to a lucrative career. Even the most passionate code aficionados don’t dream of variables or syntax — they want to make a website, a tool, a game. For years, the career upside was impossible to ignore. You could land a stable SWE job, bootstrap your own app, or join a buzzy startup as a first hire.
Generative AI flipped the script. AI now handles the repetitive tasks that used to define entry-level developer roles. At the same time, the barrier to entry for coding and building is lower than ever — you can spin up a working prototype with just an idea and a natural language prompt.
This shift hasn’t eliminated the desire to code, but it’s changed what and who coding is for. If you’re not learning to land a junior dev role, you’re learning to build the thing you’ve been imagining, to add a technical skill to your existing career, or to understand the tools you’re already using at work. And here’s the catch: those goals all require understanding your code, not just having code that works.
At Codecademy, all of these changes excite us about the future of learning to code. We’re introducing the AI Builder, a new project-based learning tool that flips the script by teaching you how to work with AI-generated code from the start. Our approach brings together the immediacy of modern AI tools and the rigor of real instructional design.
Why we created the AI Builder
AI’s speed and efficiency often come with a tradeoff; you can get working code immediately, but you don’t really know what it’s giving you or why it’s built a certain way. Developers use the term “vibe coding” to describe this phenomenon — it’s fast, fun, but shallow; great for demos, less great for long-term skill-building.
If your goal is to understand what you’re building, generic AI output alone won’t get you there. And the more you push these tools into real-world complexity, “the harder it is for them to give you exactly what you want,” says Zoe Bachman, Head of Learning at Codecademy.
With the AI Builder you get an education along with the AI output. In the workspace, you can toggle between two tabs: Build, where you work directly with a project and can modify and change code in real time; and Learn, where you get a personalized learning roadmap that’s based on your project.
“We pair the experience of having a working app with a learning path that allows you to reverse engineer how it’s built, so you can deeply understand it and modify it confidently,” Zoe says. We’re calling our hybrid approach to learning-driven development “vibe learning” — it’s powered by AI guidance but rooted in learning science.
Build first; learn continuously
With AI Builder, you start with what you want to do: build the thing in your head. Whether that’s a habit tracker, a portfolio site, or the seed of a bigger idea, you don’t need to have prior coding knowledge to learn and build with the AI Builder. In other words, there are no pre-requisites for creation.
You create a prototype by typing what you’d like to create in natural language. The AI chatbot will ask a few clarifying questions about your needs and overall goal before generating the project. Once the project is created, you can use the chat function to continue describing what you want. (You’re also welcome to go right into the code and start making changes if you already know your way around!)
“It was fun to build something so quickly and be able to see the code and a learning plan for it,” says Grace Krishna, a Code Crew member who beta tested the AI Builder.
When you need clarity on what’s going on behind the scenes in your code, or you hit a wall with AI, that’s a great time to flip over to the Learn tab.
We’re calling our hybrid approach to learning-driven development ‘vibe learning’ — it’s powered by AI guidance but rooted in learning science.
Your project becomes the curriculum
Rather than teaching concepts in the abstract and hoping learners translate them later, AI Builder removes that translation tax entirely. “We’re showing you specifically your code from your project and helping you understand it,” Zoe says.
To build that personalized curriculum, the AI Builder breaks your project’s code into clear milestones and tasks. For each task, it generates an interactive learning loop, which is an activity designed to help you form a mental model of what your specific code is doing.
These loops help you understand the logic behind each part of your project, so you can confidently apply the same thinking to other sections, or even future projects. This approach also ensures everything you learn is directly relevant to what you’re making — so you don’t have to guess when you’ll ever use this.
Why this is vibe learning (not vibe coding)
A key misconception about AI‑assisted development is that it makes learning superficial. AI Builder challenges that by grounding the entire experience in learning science rather than simple code generation. Our entire system is intentionally designed for you to retain knowledge. So, while it might not feel like you’re taking a course, you’re absorbing key concepts just by interacting with AI-generated code.
A Socratic AI, not an answer-spitting chatbot
Our educational AI chatbot is designed to guide you toward an answer through an in-depth questioning approach that’s based on the Socratic method of teaching. Instead of spitting out shortcuts or answers like AI typically does, you get strategic nudges, hints, and questions that build durable mental models.
Research on AI in education shows that just providing an answer makes it harder for learners to retain the information on their own. Zoe compares the Socratic AI to “a personalized tutor, facilitating you acquiring more knowledge, so you’re not totally left on your own.” Our method encourages you to think critically so you really grasp the concepts and can continue to use them in the real world.
Learning loops with real instructional design
Behind the scenes, every learning loop in the Learn tab is built on proven frameworks like inductive learning and the 5E model, a popular STEM teaching framework that’s shorthand for engage, explore, explain, elaborate, and evaluate.
You’ll notice that the questions and exercises in the Learn tab feel different than the rest of our courses and paths, and that’s intentional. “The learning loops are designed very well — they get you there inductively,” Zoe says. They’re exploratory without being overwhelming, and evaluative without feeling like tests.
Negar Vahid, a beta tester for the AI Builder appreciated the AI’s interactive question format. “The question-based learning feels engaging, and the starter project it builds is simple but useful,” she says.
This structure ensures you don’t develop the wrong mental models — a known risk in fully constructivist or student-centered environments — while still giving you the freedom to explore.
Why learn when AI can build?
There are some projects that are well-suited for simply vibe coding, like making a personal HTML website or a single-use script to automate a one-time task. Tools like Lovable and v0 are suited exactly for these types of projects.
The longer your code needs to live, and the more complex your project becomes, the more you need to actually understand what you’re building. Joe Holmes, Codecademy Curriculum Developer in the AI and machine learning domain, uses the term “ignorance debt” to describe what happens when you don’t:
“It’s like tech debt squared. It’s much, much worse,” Joe says. “You don’t know what kind of code is coming out. You just are only looking at: Does this kind of generally appear to be what I asked for? You don’t know if there are security flaws. You don’t know if there are performance flaws. You don’t know if you’re leaking sensitive information. You don’t know how to fix anything.”
The tipping point comes down to two factors: complexity and time. If you’re developing software professionally, you’re legally responsible for the code you output. If you’re building something that will serve actual users, you need to be accountable for security, performance, and maintainability. And if your project will need updates or fixes over time (which most do) understanding your codebase becomes essential, not optional.
The good news? Learning doesn’t have to feel like eating your vegetables. “Kids hate veggies and broccoli because we don’t cook it well enough to make it tasty when we first introduce it to them,” says Nhi Pham, Codecademy Curriculum Developer. The same is true for teaching AI: “If you do it well, you’re inspiring people to have these very hygienic practices when working with AI,” she says.
That’s exactly what AI Builder is designed to do — make learning feel as immediate and rewarding as building, so you develop good habits from the start rather than building a lifelong aversion to understanding your own code.
Get started with the AI Builder
AI isn’t a replacement for learning, it’s a tool — and a powerful one when it comes to education. Our new AI Builder allows for “just‑in‑time learning that’s highly personalized,” Zoe says. Even the best teachers or bootcamps can’t deliver that for every learner, on every project, instantly. Perhaps the most exciting vision is how AI changes what a learning environment can be.
Zoe described it beautifully: “I imagine the AI Builder as a workspace… like having all your resources around you and an AI tutor in the background.”
That’s the shift: from learning before you build to learning while you build. We can’t wait to see what you create.
The Latest Insight – Learning Systems
Musings.
Over the past few months, I’ve been testing different types of posts, zeroing in on multiple subjects that I find interesting, or that could be of interest, and that are definitely of value to the blog’s readers.
Some I see as strong, others clearly have reached the dud level.
I’ve always been a risk taker when it comes to training, learning, and its integration with online learning.
E-Learning started out as an umbrella term covering everything from learning systems to authoring tools and content.
Today?
Vendors refer to it as ‘courses and content,’ and when it comes to videos, they list them as content, not under the e-learning term, but just video.
It’s definitely frustrating because any type of content online, using the now-e-learning as content/courses moniker, is, uh, e-learning.
I spoke to a dear friend of mine, Juliette Denny, yesterday, and we both said the same thing about learning.
These days, it feels like we have to go back and teach L&D, Training, and HR teams—especially those new to learning—about the different types of learning and training methods that actually matter.
We seem to have lost the art of training and understanding e-learning, as well as the different models of learning and training.
I am one of the people (a large group) who know what Kirkpatrick is.
Honestly, I think it’s time to move on from it.
While it’s a decent approach, especially for e-learning, it was originally meant for instructor-led training.
Let me say that again: instructor-led training.
ADDIE is another method designed for instructor-led training, but many instructional designers and e-learning developers still use it when building content.
Vendors with built-in content creators, whether acquired or built in-house, lack even the basics of effective instructional design, so they don’t need someone to research outdated throwbacks to ILT methods.
I think Adobe Studio is partly to blame, since they kicked off the PowerPoint-style approach.
Terms like ‘slides’ replaced the old chapter, page, and scenario structure—what some used to call ‘lessons.’
After Studio, Rapid Content Authoring Tools (RCAT) really took off.
There was a funny moment when Studio claimed their tool couldn’t do something, but someone from Articulate made a website showing exactly how to do it.
I always liked that.
Back to learning methods: I’ve seen vendors promote Kirkpatrick or Bloom as part of their learning experience, but they often forget that most people in L&D, Training, or HR today probably don’t even know what those are.
If a vendor doesn’t realize that someone running L&D—like a CLO—might come from an Organizational Development background, why would they assume that person is an expert in Bloom or Kirkpatrick?
In my opinion, Gagne is by far the best learning methodology out there.
It’s easy to follow and understand, and it works much better for content development and learning strategy than any other method I’ve seen.
Vendors should understand learning methods.
Even though many were designed for instructor-led training, Gagne, for example, fits better with online learning than the rest.
Vendors need to take the time to learn about effective, up-to-date learning methods.
Many vendors don’t have this knowledge, and that’s a big problem in the market right now.
Case in Point
I saw Opus the other day.
They focus on the services industry, which is a smart choice.
I hope they stick with it instead of branching out too soon.
While I was quite intrigued about Opus – it is a mobile app on the learner side, which can be accessed today, whether you have an Apple or Android device. For some reason, on my Android, when I entered my number to gain access, it sent me to the iPhone store.
Highly likely, this is a bug.
I see a lot of potential with this app, but it’s missing an on/off sync feature.
I get the concerns about phone cache, but after watching and downloading lots of videos, I’ve never had to clear it.
A quick search or typing ‘clean cache’ into your phone takes about 30 seconds, and it’s done.
If cache is a big concern, Opus could simply show users how to clear it instead of holding back on an on/off sync feature.
One of the Opus founders comes from the restaurant industry, so they really understand their market and the challenges frontline workers face.
If the store has awful internet connectivity, or a bar or restaurant, or whatever, an hourly employee isn’t going to be able to do what is asked of them.
I’ll admit, we ran out of time before I could see the back-end, but I’m looking forward to checking it out.
One thing that really surprised me was how much engagement Opus gets from learners.
Even though they say they don’t have gamification, they actually do have an element -a leaderboard.
Don’t get me wrong—Opus is a vendor to watch, especially since they’re in a niche like services, which includes places like amusement parks that many vendors overlook because they don’t see the revenue potential.
Shifting Gears
Docebo, which I really like, is moving more into the L&D segment than before—at least in their messaging.
Despite their audience being 60% in customer training and partner enablement, I always saw the system leaning toward L&D.
They are not the only Combos systems that do it.
I saw the latest version (with what is out today, what will be released and announced at their show, and what is rolling out later this year).
A lot is Embargo – which means I can’t tell you – something any analyst worth their weight should always do, regardless of whether the vendor is public or not.
Still, what I did hear—and Docebo isn’t the only vendor to mention this—is that they’re talking to people like the head of HR about their system.
There’s a saying—and I’m not the only one who says it: Training doesn’t like working with L&D, L&D doesn’t like working with Training, and nobody likes working with HR.
Too many companies put L&D under HR, but it’s a terrible fit.
I think companies that keep L&D separate from HR do a better job for their employees.
That’s because someone leading L&D is expected to know much more about learning approaches—especially e-learning—than someone in HR.
HR is helpful for sending files or data to L&D, especially if the learning system isn’t connected to the HRIS or HCM.
Toss in IT, and things often go wrong.
IT often sees a learning system as another ERP nightmare.
Then you have IT wanting to manage everything, HR wanting control, and L&D getting blamed if anything goes wrong.
Career Management
There’s a new term out there—though it’s really an old one—called career development.
When I see ‘career management’ listed as a feature in a learning system, it clearly points to L&D, with a bit of HR influence.
This basically turns the system into a Talent Development platform, especially if it offers opportunities, goal management, and similar features—whether as add-ons or built-in.
There’s nothing wrong with Talent Development.
I still see it as a growing market—Degreed, for example, now calls itself a Talent Development System or Platform.
Cypher Learning, which serves both markets and has about 80% of its audience in L&D, now wants to focus more on customer training and partner enablement.
But when you add career management, it doesn’t exactly make someone say, ‘Wow, I need this platform for my clients.’
B2C
Now, there are combo systems that focus heavily on customer training and partner enablement, especially those that see growth potential in the B2C segment.
Think about all the influencers who not only sell products—like infomercial 2.0—but also sell their content to anyone interested.
What platform are they using to do it?
Vendors need to think creatively.
The industry is fragmented, and you can be strong in niche segments if you are willing to make changes and tweaks, for example, in B2C.
These clients don’t care about skills or career management.
They care about making money, so vendors need to provide insights about their buyers.
One vendor I see as a player here is Eurekos.
They are IMO, the #1 learning system for customer training/partner enablement – because that is their only focus.
The system is built for this, with the right features and data points for customer training and partner enablement.
Expect to see a few more vendors go after the B2C market for influencers—not just training consultants or instructors, since there are already vendors for that.
Bottom Line
When it comes to AI Assistants – aka Knowledge Management, you want to have it include SCORM Parsing.
KnovaLearn, Metalark.AI, and Talvi.ai already provide it, with the latter also supporting xAPI.
In my view, instructor-led training isn’t the most effective learning method overall.
Web-Based Training (WBT), also known as e-learning or online learning, gives you insight into what learners or customers know and provides metrics to back it up.
People are not robots, thankfully.
You can’t expect to remember everything from just one instructor-led training session.
You won’t reach true understanding, go at your own pace, or access the content whenever and wherever you want in a traditional classroom setting.
You can make mistakes without the fear of being called out.
That’s the power of online learning and training.
It’s not about AI (a tool, not a universal replacement for an LMS or any other learning system).
It’s about the learner themselves.
What do they know and don’t know?
What can you do to enable them to retain and synthesize the information?
What data is relevant, what content is of value?
And what does it all mean?
E-Learning 24/7
Why the Future of Learning Starts with Building
Coding has always served two purposes: the intrinsic drive to build something, and the practical path to a lucrative career. Even the most passionate code aficionados don’t dream of variables or syntax — they want to make a website, a tool, a game. For years, the career upside was impossible to ignore. You could land a stable SWE job, bootstrap your own app, or join a buzzy startup as a first hire.
Generative AI flipped the script. AI now handles the repetitive tasks that used to define entry-level developer roles. At the same time, the barrier to entry for coding and building is lower than ever — you can spin up a working prototype with just an idea and a natural language prompt.
This shift hasn’t eliminated the desire to code, but it’s changed what and who coding is for. If you’re not learning to land a junior dev role, you’re learning to build the thing you’ve been imagining, to add a technical skill to your existing career, or to understand the tools you’re already using at work. And here’s the catch: those goals all require understanding your code, not just having code that works.
At Codecademy, all of these changes excite us about the future of learning to code. We’re introducing the AI Builder, a new project-based learning tool that flips the script by teaching you how to work with AI-generated code from the start. Our approach brings together the immediacy of modern AI tools and the rigor of real instructional design.
Why we created the AI Builder
AI’s speed and efficiency often come with a tradeoff; you can get working code immediately, but you don’t really know what it’s giving you or why it’s built a certain way. Developers use the term “vibe coding” to describe this phenomenon — it’s fast, fun, but shallow; great for demos, less great for long-term skill-building.
If your goal is to understand what you’re building, generic AI output alone won’t get you there. And the more you push these tools into real-world complexity, “the harder it is for them to give you exactly what you want,” says Zoe Bachman, Head of Learning at Codecademy.
With the AI Builder you get an education along with the AI output. In the workspace, you can toggle between two tabs: Build, where you work directly with a project and can modify and change code in real time; and Learn, where you get a personalized learning roadmap that’s based on your project.
“We pair the experience of having a working app with a learning path that allows you to reverse engineer how it’s built, so you can deeply understand it and modify it confidently,” Zoe says. We’re calling our hybrid approach to learning-driven development “vibe learning” — it’s powered by AI guidance but rooted in learning science.
Build first; learn continuously
With AI Builder, you start with what you want to do: build the thing in your head. Whether that’s a habit tracker, a portfolio site, or the seed of a bigger idea, you don’t need to have prior coding knowledge to learn and build with the AI Builder. In other words, there are no pre-requisites for creation.
You create a prototype by typing what you’d like to create in natural language. The AI chatbot will ask a few clarifying questions about your needs and overall goal before generating the project. Once the project is created, you can use the chat function to continue describing what you want. (You’re also welcome to go right into the code and start making changes if you already know your way around!)
“It was fun to build something so quickly and be able to see the code and a learning plan for it,” says Grace Krishna, a Code Crew member who beta tested the AI Builder.
When you need clarity on what’s going on behind the scenes in your code, or you hit a wall with AI, that’s a great time to flip over to the Learn tab.
We’re calling our hybrid approach to learning-driven development ‘vibe learning’ — it’s powered by AI guidance but rooted in learning science.
Your project becomes the curriculum
Rather than teaching concepts in the abstract and hoping learners translate them later, AI Builder removes that translation tax entirely. “We’re showing you specifically your code from your project and helping you understand it,” Zoe says.
To build that personalized curriculum, the AI Builder breaks your project’s code into clear milestones and tasks. For each task, it generates an interactive learning loop, which is an activity designed to help you form a mental model of what your specific code is doing.
These loops help you understand the logic behind each part of your project, so you can confidently apply the same thinking to other sections, or even future projects. This approach also ensures everything you learn is directly relevant to what you’re making — so you don’t have to guess when you’ll ever use this.
Why this is vibe learning (not vibe coding)
A key misconception about AI‑assisted development is that it makes learning superficial. AI Builder challenges that by grounding the entire experience in learning science rather than simple code generation. Our entire system is intentionally designed for you to retain knowledge. So, while it might not feel like you’re taking a course, you’re absorbing key concepts just by interacting with AI-generated code.
A Socratic AI, not an answer-spitting chatbot
Our educational AI chatbot is designed to guide you toward an answer through an in-depth questioning approach that’s based on the Socratic method of teaching. Instead of spitting out shortcuts or answers like AI typically does, you get strategic nudges, hints, and questions that build durable mental models.
Research on AI in education shows that just providing an answer makes it harder for learners to retain the information on their own. Zoe compares the Socratic AI to “a personalized tutor, facilitating you acquiring more knowledge, so you’re not totally left on your own.” Our method encourages you to think critically so you really grasp the concepts and can continue to use them in the real world.
Learning loops with real instructional design
Behind the scenes, every learning loop in the Learn tab is built on proven frameworks like inductive learning and the 5E model, a popular STEM teaching framework that’s shorthand for engage, explore, explain, elaborate, and evaluate.
You’ll notice that the questions and exercises in the Learn tab feel different than the rest of our courses and paths, and that’s intentional. “The learning loops are designed very well — they get you there inductively,” Zoe says. They’re exploratory without being overwhelming, and evaluative without feeling like tests.
Negar Vahid, a beta tester for the AI Builder appreciated the AI’s interactive question format. “The question-based learning feels engaging, and the starter project it builds is simple but useful,” she says.
This structure ensures you don’t develop the wrong mental models — a known risk in fully constructivist or student-centered environments — while still giving you the freedom to explore.
Why learn when AI can build?
There are some projects that are well-suited for simply vibe coding, like making a personal HTML website or a single-use script to automate a one-time task. Tools like Lovable and v0 are suited exactly for these types of projects.
The longer your code needs to live, and the more complex your project becomes, the more you need to actually understand what you’re building. Joe Holmes, Codecademy Curriculum Developer in the AI and machine learning domain, uses the term “ignorance debt” to describe what happens when you don’t:
“It’s like tech debt squared. It’s much, much worse,” Joe says. “You don’t know what kind of code is coming out. You just are only looking at: Does this kind of generally appear to be what I asked for? You don’t know if there are security flaws. You don’t know if there are performance flaws. You don’t know if you’re leaking sensitive information. You don’t know how to fix anything.”
The tipping point comes down to two factors: complexity and time. If you’re developing software professionally, you’re legally responsible for the code you output. If you’re building something that will serve actual users, you need to be accountable for security, performance, and maintainability. And if your project will need updates or fixes over time (which most do) understanding your codebase becomes essential, not optional.
The good news? Learning doesn’t have to feel like eating your vegetables. “Kids hate veggies and broccoli because we don’t cook it well enough to make it tasty when we first introduce it to them,” says Nhi Pham, Codecademy Curriculum Developer. The same is true for teaching AI: “If you do it well, you’re inspiring people to have these very hygienic practices when working with AI,” she says.
That’s exactly what AI Builder is designed to do — make learning feel as immediate and rewarding as building, so you develop good habits from the start rather than building a lifelong aversion to understanding your own code.
Get started with the AI Builder
AI isn’t a replacement for learning, it’s a tool — and a powerful one when it comes to education. Our new AI Builder allows for “just‑in‑time learning that’s highly personalized,” Zoe says. Even the best teachers or bootcamps can’t deliver that for every learner, on every project, instantly. Perhaps the most exciting vision is how AI changes what a learning environment can be.
Zoe described it beautifully: “I imagine the AI Builder as a workspace… like having all your resources around you and an AI tutor in the background.”
That’s the shift: from learning before you build to learning while you build. We can’t wait to see what you create.
Why the Future of Learning Starts with Building
Coding has always served two purposes: the intrinsic drive to build something, and the practical path to a lucrative career. Even the most passionate code aficionados don’t dream of variables or syntax — they want to make a website, a tool, a game. For years, the career upside was impossible to ignore. You could land a stable SWE job, bootstrap your own app, or join a buzzy startup as a first hire.
Generative AI flipped the script. AI now handles the repetitive tasks that used to define entry-level developer roles. At the same time, the barrier to entry for coding and building is lower than ever — you can spin up a working prototype with just an idea and a natural language prompt.
This shift hasn’t eliminated the desire to code, but it’s changed what and who coding is for. If you’re not learning to land a junior dev role, you’re learning to build the thing you’ve been imagining, to add a technical skill to your existing career, or to understand the tools you’re already using at work. And here’s the catch: those goals all require understanding your code, not just having code that works.
At Codecademy, all of these changes excite us about the future of learning to code. We’re introducing the AI Builder, a new project-based learning tool that flips the script by teaching you how to work with AI-generated code from the start. Our approach brings together the immediacy of modern AI tools and the rigor of real instructional design.
Why we created the AI Builder
AI’s speed and efficiency often come with a tradeoff; you can get working code immediately, but you don’t really know what it’s giving you or why it’s built a certain way. Developers use the term “vibe coding” to describe this phenomenon — it’s fast, fun, but shallow; great for demos, less great for long-term skill-building.
If your goal is to understand what you’re building, generic AI output alone won’t get you there. And the more you push these tools into real-world complexity, “the harder it is for them to give you exactly what you want,” says Zoe Bachman, Head of Learning at Codecademy.
With the AI Builder you get an education along with the AI output. In the workspace, you can toggle between two tabs: Build, where you work directly with a project and can modify and change code in real time; and Learn, where you get a personalized learning roadmap that’s based on your project.
“We pair the experience of having a working app with a learning path that allows you to reverse engineer how it’s built, so you can deeply understand it and modify it confidently,” Zoe says. We’re calling our hybrid approach to learning-driven development “vibe learning” — it’s powered by AI guidance but rooted in learning science.
Build first; learn continuously
With AI Builder, you start with what you want to do: build the thing in your head. Whether that’s a habit tracker, a portfolio site, or the seed of a bigger idea, you don’t need to have prior coding knowledge to learn and build with the AI Builder. In other words, there are no pre-requisites for creation.
You create a prototype by typing what you’d like to create in natural language. The AI chatbot will ask a few clarifying questions about your needs and overall goal before generating the project. Once the project is created, you can use the chat function to continue describing what you want. (You’re also welcome to go right into the code and start making changes if you already know your way around!)
“It was fun to build something so quickly and be able to see the code and a learning plan for it,” says Grace Krishna, a Code Crew member who beta tested the AI Builder.
When you need clarity on what’s going on behind the scenes in your code, or you hit a wall with AI, that’s a great time to flip over to the Learn tab.
We’re calling our hybrid approach to learning-driven development ‘vibe learning’ — it’s powered by AI guidance but rooted in learning science.
Your project becomes the curriculum
Rather than teaching concepts in the abstract and hoping learners translate them later, AI Builder removes that translation tax entirely. “We’re showing you specifically your code from your project and helping you understand it,” Zoe says.
To build that personalized curriculum, the AI Builder breaks your project’s code into clear milestones and tasks. For each task, it generates an interactive learning loop, which is an activity designed to help you form a mental model of what your specific code is doing.
These loops help you understand the logic behind each part of your project, so you can confidently apply the same thinking to other sections, or even future projects. This approach also ensures everything you learn is directly relevant to what you’re making — so you don’t have to guess when you’ll ever use this.
Why this is vibe learning (not vibe coding)
A key misconception about AI‑assisted development is that it makes learning superficial. AI Builder challenges that by grounding the entire experience in learning science rather than simple code generation. Our entire system is intentionally designed for you to retain knowledge. So, while it might not feel like you’re taking a course, you’re absorbing key concepts just by interacting with AI-generated code.
A Socratic AI, not an answer-spitting chatbot
Our educational AI chatbot is designed to guide you toward an answer through an in-depth questioning approach that’s based on the Socratic method of teaching. Instead of spitting out shortcuts or answers like AI typically does, you get strategic nudges, hints, and questions that build durable mental models.
Research on AI in education shows that just providing an answer makes it harder for learners to retain the information on their own. Zoe compares the Socratic AI to “a personalized tutor, facilitating you acquiring more knowledge, so you’re not totally left on your own.” Our method encourages you to think critically so you really grasp the concepts and can continue to use them in the real world.
Learning loops with real instructional design
Behind the scenes, every learning loop in the Learn tab is built on proven frameworks like inductive learning and the 5E model, a popular STEM teaching framework that’s shorthand for engage, explore, explain, elaborate, and evaluate.
You’ll notice that the questions and exercises in the Learn tab feel different than the rest of our courses and paths, and that’s intentional. “The learning loops are designed very well — they get you there inductively,” Zoe says. They’re exploratory without being overwhelming, and evaluative without feeling like tests.
Negar Vahid, a beta tester for the AI Builder appreciated the AI’s interactive question format. “The question-based learning feels engaging, and the starter project it builds is simple but useful,” she says.
This structure ensures you don’t develop the wrong mental models — a known risk in fully constructivist or student-centered environments — while still giving you the freedom to explore.
Why learn when AI can build?
There are some projects that are well-suited for simply vibe coding, like making a personal HTML website or a single-use script to automate a one-time task. Tools like Lovable and v0 are suited exactly for these types of projects.
The longer your code needs to live, and the more complex your project becomes, the more you need to actually understand what you’re building. Joe Holmes, Codecademy Curriculum Developer in the AI and machine learning domain, uses the term “ignorance debt” to describe what happens when you don’t:
“It’s like tech debt squared. It’s much, much worse,” Joe says. “You don’t know what kind of code is coming out. You just are only looking at: Does this kind of generally appear to be what I asked for? You don’t know if there are security flaws. You don’t know if there are performance flaws. You don’t know if you’re leaking sensitive information. You don’t know how to fix anything.”
The tipping point comes down to two factors: complexity and time. If you’re developing software professionally, you’re legally responsible for the code you output. If you’re building something that will serve actual users, you need to be accountable for security, performance, and maintainability. And if your project will need updates or fixes over time (which most do) understanding your codebase becomes essential, not optional.
The good news? Learning doesn’t have to feel like eating your vegetables. “Kids hate veggies and broccoli because we don’t cook it well enough to make it tasty when we first introduce it to them,” says Nhi Pham, Codecademy Curriculum Developer. The same is true for teaching AI: “If you do it well, you’re inspiring people to have these very hygienic practices when working with AI,” she says.
That’s exactly what AI Builder is designed to do — make learning feel as immediate and rewarding as building, so you develop good habits from the start rather than building a lifelong aversion to understanding your own code.
Get started with the AI Builder
AI isn’t a replacement for learning, it’s a tool — and a powerful one when it comes to education. Our new AI Builder allows for “just‑in‑time learning that’s highly personalized,” Zoe says. Even the best teachers or bootcamps can’t deliver that for every learner, on every project, instantly. Perhaps the most exciting vision is how AI changes what a learning environment can be.
Zoe described it beautifully: “I imagine the AI Builder as a workspace… like having all your resources around you and an AI tutor in the background.”
That’s the shift: from learning before you build to learning while you build. We can’t wait to see what you create.
Why the Future of Learning Starts with Building
Coding has always served two purposes: the intrinsic drive to build something, and the practical path to a lucrative career. Even the most passionate code aficionados don’t dream of variables or syntax — they want to make a website, a tool, a game. For years, the career upside was impossible to ignore. You could land a stable SWE job, bootstrap your own app, or join a buzzy startup as a first hire.
Generative AI flipped the script. AI now handles the repetitive tasks that used to define entry-level developer roles. At the same time, the barrier to entry for coding and building is lower than ever — you can spin up a working prototype with just an idea and a natural language prompt.
This shift hasn’t eliminated the desire to code, but it’s changed what and who coding is for. If you’re not learning to land a junior dev role, you’re learning to build the thing you’ve been imagining, to add a technical skill to your existing career, or to understand the tools you’re already using at work. And here’s the catch: those goals all require understanding your code, not just having code that works.
At Codecademy, all of these changes excite us about the future of learning to code. We’re introducing the AI Builder, a new project-based learning tool that flips the script by teaching you how to work with AI-generated code from the start. Our approach brings together the immediacy of modern AI tools and the rigor of real instructional design.
Why we created the AI Builder
AI’s speed and efficiency often come with a tradeoff; you can get working code immediately, but you don’t really know what it’s giving you or why it’s built a certain way. Developers use the term “vibe coding” to describe this phenomenon — it’s fast, fun, but shallow; great for demos, less great for long-term skill-building.
If your goal is to understand what you’re building, generic AI output alone won’t get you there. And the more you push these tools into real-world complexity, “the harder it is for them to give you exactly what you want,” says Zoe Bachman, Head of Learning at Codecademy.
With the AI Builder you get an education along with the AI output. In the workspace, you can toggle between two tabs: Build, where you work directly with a project and can modify and change code in real time; and Learn, where you get a personalized learning roadmap that’s based on your project.
“We pair the experience of having a working app with a learning path that allows you to reverse engineer how it’s built, so you can deeply understand it and modify it confidently,” Zoe says. We’re calling our hybrid approach to learning-driven development “vibe learning” — it’s powered by AI guidance but rooted in learning science.
Build first; learn continuously
With AI Builder, you start with what you want to do: build the thing in your head. Whether that’s a habit tracker, a portfolio site, or the seed of a bigger idea, you don’t need to have prior coding knowledge to learn and build with the AI Builder. In other words, there are no pre-requisites for creation.
You create a prototype by typing what you’d like to create in natural language. The AI chatbot will ask a few clarifying questions about your needs and overall goal before generating the project. Once the project is created, you can use the chat function to continue describing what you want. (You’re also welcome to go right into the code and start making changes if you already know your way around!)
“It was fun to build something so quickly and be able to see the code and a learning plan for it,” says Grace Krishna, a Code Crew member who beta tested the AI Builder.
When you need clarity on what’s going on behind the scenes in your code, or you hit a wall with AI, that’s a great time to flip over to the Learn tab.
We’re calling our hybrid approach to learning-driven development ‘vibe learning’ — it’s powered by AI guidance but rooted in learning science.
Your project becomes the curriculum
Rather than teaching concepts in the abstract and hoping learners translate them later, AI Builder removes that translation tax entirely. “We’re showing you specifically your code from your project and helping you understand it,” Zoe says.
To build that personalized curriculum, the AI Builder breaks your project’s code into clear milestones and tasks. For each task, it generates an interactive learning loop, which is an activity designed to help you form a mental model of what your specific code is doing.
These loops help you understand the logic behind each part of your project, so you can confidently apply the same thinking to other sections, or even future projects. This approach also ensures everything you learn is directly relevant to what you’re making — so you don’t have to guess when you’ll ever use this.
Why this is vibe learning (not vibe coding)
A key misconception about AI‑assisted development is that it makes learning superficial. AI Builder challenges that by grounding the entire experience in learning science rather than simple code generation. Our entire system is intentionally designed for you to retain knowledge. So, while it might not feel like you’re taking a course, you’re absorbing key concepts just by interacting with AI-generated code.
A Socratic AI, not an answer-spitting chatbot
Our educational AI chatbot is designed to guide you toward an answer through an in-depth questioning approach that’s based on the Socratic method of teaching. Instead of spitting out shortcuts or answers like AI typically does, you get strategic nudges, hints, and questions that build durable mental models.
Research on AI in education shows that just providing an answer makes it harder for learners to retain the information on their own. Zoe compares the Socratic AI to “a personalized tutor, facilitating you acquiring more knowledge, so you’re not totally left on your own.” Our method encourages you to think critically so you really grasp the concepts and can continue to use them in the real world.
Learning loops with real instructional design
Behind the scenes, every learning loop in the Learn tab is built on proven frameworks like inductive learning and the 5E model, a popular STEM teaching framework that’s shorthand for engage, explore, explain, elaborate, and evaluate.
You’ll notice that the questions and exercises in the Learn tab feel different than the rest of our courses and paths, and that’s intentional. “The learning loops are designed very well — they get you there inductively,” Zoe says. They’re exploratory without being overwhelming, and evaluative without feeling like tests.
Negar Vahid, a beta tester for the AI Builder appreciated the AI’s interactive question format. “The question-based learning feels engaging, and the starter project it builds is simple but useful,” she says.
This structure ensures you don’t develop the wrong mental models — a known risk in fully constructivist or student-centered environments — while still giving you the freedom to explore.
Why learn when AI can build?
There are some projects that are well-suited for simply vibe coding, like making a personal HTML website or a single-use script to automate a one-time task. Tools like Lovable and v0 are suited exactly for these types of projects.
The longer your code needs to live, and the more complex your project becomes, the more you need to actually understand what you’re building. Joe Holmes, Codecademy Curriculum Developer in the AI and machine learning domain, uses the term “ignorance debt” to describe what happens when you don’t:
“It’s like tech debt squared. It’s much, much worse,” Joe says. “You don’t know what kind of code is coming out. You just are only looking at: Does this kind of generally appear to be what I asked for? You don’t know if there are security flaws. You don’t know if there are performance flaws. You don’t know if you’re leaking sensitive information. You don’t know how to fix anything.”
The tipping point comes down to two factors: complexity and time. If you’re developing software professionally, you’re legally responsible for the code you output. If you’re building something that will serve actual users, you need to be accountable for security, performance, and maintainability. And if your project will need updates or fixes over time (which most do) understanding your codebase becomes essential, not optional.
The good news? Learning doesn’t have to feel like eating your vegetables. “Kids hate veggies and broccoli because we don’t cook it well enough to make it tasty when we first introduce it to them,” says Nhi Pham, Codecademy Curriculum Developer. The same is true for teaching AI: “If you do it well, you’re inspiring people to have these very hygienic practices when working with AI,” she says.
That’s exactly what AI Builder is designed to do — make learning feel as immediate and rewarding as building, so you develop good habits from the start rather than building a lifelong aversion to understanding your own code.
Get started with the AI Builder
AI isn’t a replacement for learning, it’s a tool — and a powerful one when it comes to education. Our new AI Builder allows for “just‑in‑time learning that’s highly personalized,” Zoe says. Even the best teachers or bootcamps can’t deliver that for every learner, on every project, instantly. Perhaps the most exciting vision is how AI changes what a learning environment can be.
Zoe described it beautifully: “I imagine the AI Builder as a workspace… like having all your resources around you and an AI tutor in the background.”
That’s the shift: from learning before you build to learning while you build. We can’t wait to see what you create.
Why the Future of Learning Starts with Building
Coding has always served two purposes: the intrinsic drive to build something, and the practical path to a lucrative career. Even the most passionate code aficionados don’t dream of variables or syntax — they want to make a website, a tool, a game. For years, the career upside was impossible to ignore. You could land a stable SWE job, bootstrap your own app, or join a buzzy startup as a first hire.
Generative AI flipped the script. AI now handles the repetitive tasks that used to define entry-level developer roles. At the same time, the barrier to entry for coding and building is lower than ever — you can spin up a working prototype with just an idea and a natural language prompt.
This shift hasn’t eliminated the desire to code, but it’s changed what and who coding is for. If you’re not learning to land a junior dev role, you’re learning to build the thing you’ve been imagining, to add a technical skill to your existing career, or to understand the tools you’re already using at work. And here’s the catch: those goals all require understanding your code, not just having code that works.
At Codecademy, all of these changes excite us about the future of learning to code. We’re introducing the AI Builder, a new project-based learning tool that flips the script by teaching you how to work with AI-generated code from the start. Our approach brings together the immediacy of modern AI tools and the rigor of real instructional design.
Why we created the AI Builder
AI’s speed and efficiency often come with a tradeoff; you can get working code immediately, but you don’t really know what it’s giving you or why it’s built a certain way. Developers use the term “vibe coding” to describe this phenomenon — it’s fast, fun, but shallow; great for demos, less great for long-term skill-building.
If your goal is to understand what you’re building, generic AI output alone won’t get you there. And the more you push these tools into real-world complexity, “the harder it is for them to give you exactly what you want,” says Zoe Bachman, Head of Learning at Codecademy.
With the AI Builder you get an education along with the AI output. In the workspace, you can toggle between two tabs: Build, where you work directly with a project and can modify and change code in real time; and Learn, where you get a personalized learning roadmap that’s based on your project.
“We pair the experience of having a working app with a learning path that allows you to reverse engineer how it’s built, so you can deeply understand it and modify it confidently,” Zoe says. We’re calling our hybrid approach to learning-driven development “vibe learning” — it’s powered by AI guidance but rooted in learning science.
Build first; learn continuously
With AI Builder, you start with what you want to do: build the thing in your head. Whether that’s a habit tracker, a portfolio site, or the seed of a bigger idea, you don’t need to have prior coding knowledge to learn and build with the AI Builder. In other words, there are no pre-requisites for creation.
You create a prototype by typing what you’d like to create in natural language. The AI chatbot will ask a few clarifying questions about your needs and overall goal before generating the project. Once the project is created, you can use the chat function to continue describing what you want. (You’re also welcome to go right into the code and start making changes if you already know your way around!)
“It was fun to build something so quickly and be able to see the code and a learning plan for it,” says Grace Krishna, a Code Crew member who beta tested the AI Builder.
When you need clarity on what’s going on behind the scenes in your code, or you hit a wall with AI, that’s a great time to flip over to the Learn tab.
We’re calling our hybrid approach to learning-driven development ‘vibe learning’ — it’s powered by AI guidance but rooted in learning science.
Your project becomes the curriculum
Rather than teaching concepts in the abstract and hoping learners translate them later, AI Builder removes that translation tax entirely. “We’re showing you specifically your code from your project and helping you understand it,” Zoe says.
To build that personalized curriculum, the AI Builder breaks your project’s code into clear milestones and tasks. For each task, it generates an interactive learning loop, which is an activity designed to help you form a mental model of what your specific code is doing.
These loops help you understand the logic behind each part of your project, so you can confidently apply the same thinking to other sections, or even future projects. This approach also ensures everything you learn is directly relevant to what you’re making — so you don’t have to guess when you’ll ever use this.
Why this is vibe learning (not vibe coding)
A key misconception about AI‑assisted development is that it makes learning superficial. AI Builder challenges that by grounding the entire experience in learning science rather than simple code generation. Our entire system is intentionally designed for you to retain knowledge. So, while it might not feel like you’re taking a course, you’re absorbing key concepts just by interacting with AI-generated code.
A Socratic AI, not an answer-spitting chatbot
Our educational AI chatbot is designed to guide you toward an answer through an in-depth questioning approach that’s based on the Socratic method of teaching. Instead of spitting out shortcuts or answers like AI typically does, you get strategic nudges, hints, and questions that build durable mental models.
Research on AI in education shows that just providing an answer makes it harder for learners to retain the information on their own. Zoe compares the Socratic AI to “a personalized tutor, facilitating you acquiring more knowledge, so you’re not totally left on your own.” Our method encourages you to think critically so you really grasp the concepts and can continue to use them in the real world.
Learning loops with real instructional design
Behind the scenes, every learning loop in the Learn tab is built on proven frameworks like inductive learning and the 5E model, a popular STEM teaching framework that’s shorthand for engage, explore, explain, elaborate, and evaluate.
You’ll notice that the questions and exercises in the Learn tab feel different than the rest of our courses and paths, and that’s intentional. “The learning loops are designed very well — they get you there inductively,” Zoe says. They’re exploratory without being overwhelming, and evaluative without feeling like tests.
Negar Vahid, a beta tester for the AI Builder appreciated the AI’s interactive question format. “The question-based learning feels engaging, and the starter project it builds is simple but useful,” she says.
This structure ensures you don’t develop the wrong mental models — a known risk in fully constructivist or student-centered environments — while still giving you the freedom to explore.
Why learn when AI can build?
There are some projects that are well-suited for simply vibe coding, like making a personal HTML website or a single-use script to automate a one-time task. Tools like Lovable and v0 are suited exactly for these types of projects.
The longer your code needs to live, and the more complex your project becomes, the more you need to actually understand what you’re building. Joe Holmes, Codecademy Curriculum Developer in the AI and machine learning domain, uses the term “ignorance debt” to describe what happens when you don’t:
“It’s like tech debt squared. It’s much, much worse,” Joe says. “You don’t know what kind of code is coming out. You just are only looking at: Does this kind of generally appear to be what I asked for? You don’t know if there are security flaws. You don’t know if there are performance flaws. You don’t know if you’re leaking sensitive information. You don’t know how to fix anything.”
The tipping point comes down to two factors: complexity and time. If you’re developing software professionally, you’re legally responsible for the code you output. If you’re building something that will serve actual users, you need to be accountable for security, performance, and maintainability. And if your project will need updates or fixes over time (which most do) understanding your codebase becomes essential, not optional.
The good news? Learning doesn’t have to feel like eating your vegetables. “Kids hate veggies and broccoli because we don’t cook it well enough to make it tasty when we first introduce it to them,” says Nhi Pham, Codecademy Curriculum Developer. The same is true for teaching AI: “If you do it well, you’re inspiring people to have these very hygienic practices when working with AI,” she says.
That’s exactly what AI Builder is designed to do — make learning feel as immediate and rewarding as building, so you develop good habits from the start rather than building a lifelong aversion to understanding your own code.
Get started with the AI Builder
AI isn’t a replacement for learning, it’s a tool — and a powerful one when it comes to education. Our new AI Builder allows for “just‑in‑time learning that’s highly personalized,” Zoe says. Even the best teachers or bootcamps can’t deliver that for every learner, on every project, instantly. Perhaps the most exciting vision is how AI changes what a learning environment can be.
Zoe described it beautifully: “I imagine the AI Builder as a workspace… like having all your resources around you and an AI tutor in the background.”
That’s the shift: from learning before you build to learning while you build. We can’t wait to see what you create.
Why the Future of Learning Starts with Building
Coding has always served two purposes: the intrinsic drive to build something, and the practical path to a lucrative career. Even the most passionate code aficionados don’t dream of variables or syntax — they want to make a website, a tool, a game. For years, the career upside was impossible to ignore. You could land a stable SWE job, bootstrap your own app, or join a buzzy startup as a first hire.
Generative AI flipped the script. AI now handles the repetitive tasks that used to define entry-level developer roles. At the same time, the barrier to entry for coding and building is lower than ever — you can spin up a working prototype with just an idea and a natural language prompt.
This shift hasn’t eliminated the desire to code, but it’s changed what and who coding is for. If you’re not learning to land a junior dev role, you’re learning to build the thing you’ve been imagining, to add a technical skill to your existing career, or to understand the tools you’re already using at work. And here’s the catch: those goals all require understanding your code, not just having code that works.
At Codecademy, all of these changes excite us about the future of learning to code. We’re introducing the AI Builder, a new project-based learning tool that flips the script by teaching you how to work with AI-generated code from the start. Our approach brings together the immediacy of modern AI tools and the rigor of real instructional design.
Why we created the AI Builder
AI’s speed and efficiency often come with a tradeoff; you can get working code immediately, but you don’t really know what it’s giving you or why it’s built a certain way. Developers use the term “vibe coding” to describe this phenomenon — it’s fast, fun, but shallow; great for demos, less great for long-term skill-building.
If your goal is to understand what you’re building, generic AI output alone won’t get you there. And the more you push these tools into real-world complexity, “the harder it is for them to give you exactly what you want,” says Zoe Bachman, Head of Learning at Codecademy.
With the AI Builder you get an education along with the AI output. In the workspace, you can toggle between two tabs: Build, where you work directly with a project and can modify and change code in real time; and Learn, where you get a personalized learning roadmap that’s based on your project.
“We pair the experience of having a working app with a learning path that allows you to reverse engineer how it’s built, so you can deeply understand it and modify it confidently,” Zoe says. We’re calling our hybrid approach to learning-driven development “vibe learning” — it’s powered by AI guidance but rooted in learning science.
Build first; learn continuously
With AI Builder, you start with what you want to do: build the thing in your head. Whether that’s a habit tracker, a portfolio site, or the seed of a bigger idea, you don’t need to have prior coding knowledge to learn and build with the AI Builder. In other words, there are no pre-requisites for creation.
You create a prototype by typing what you’d like to create in natural language. The AI chatbot will ask a few clarifying questions about your needs and overall goal before generating the project. Once the project is created, you can use the chat function to continue describing what you want. (You’re also welcome to go right into the code and start making changes if you already know your way around!)
“It was fun to build something so quickly and be able to see the code and a learning plan for it,” says Grace Krishna, a Code Crew member who beta tested the AI Builder.
When you need clarity on what’s going on behind the scenes in your code, or you hit a wall with AI, that’s a great time to flip over to the Learn tab.
We’re calling our hybrid approach to learning-driven development ‘vibe learning’ — it’s powered by AI guidance but rooted in learning science.
Your project becomes the curriculum
Rather than teaching concepts in the abstract and hoping learners translate them later, AI Builder removes that translation tax entirely. “We’re showing you specifically your code from your project and helping you understand it,” Zoe says.
To build that personalized curriculum, the AI Builder breaks your project’s code into clear milestones and tasks. For each task, it generates an interactive learning loop, which is an activity designed to help you form a mental model of what your specific code is doing.
These loops help you understand the logic behind each part of your project, so you can confidently apply the same thinking to other sections, or even future projects. This approach also ensures everything you learn is directly relevant to what you’re making — so you don’t have to guess when you’ll ever use this.
Why this is vibe learning (not vibe coding)
A key misconception about AI‑assisted development is that it makes learning superficial. AI Builder challenges that by grounding the entire experience in learning science rather than simple code generation. Our entire system is intentionally designed for you to retain knowledge. So, while it might not feel like you’re taking a course, you’re absorbing key concepts just by interacting with AI-generated code.
A Socratic AI, not an answer-spitting chatbot
Our educational AI chatbot is designed to guide you toward an answer through an in-depth questioning approach that’s based on the Socratic method of teaching. Instead of spitting out shortcuts or answers like AI typically does, you get strategic nudges, hints, and questions that build durable mental models.
Research on AI in education shows that just providing an answer makes it harder for learners to retain the information on their own. Zoe compares the Socratic AI to “a personalized tutor, facilitating you acquiring more knowledge, so you’re not totally left on your own.” Our method encourages you to think critically so you really grasp the concepts and can continue to use them in the real world.
Learning loops with real instructional design
Behind the scenes, every learning loop in the Learn tab is built on proven frameworks like inductive learning and the 5E model, a popular STEM teaching framework that’s shorthand for engage, explore, explain, elaborate, and evaluate.
You’ll notice that the questions and exercises in the Learn tab feel different than the rest of our courses and paths, and that’s intentional. “The learning loops are designed very well — they get you there inductively,” Zoe says. They’re exploratory without being overwhelming, and evaluative without feeling like tests.
Negar Vahid, a beta tester for the AI Builder appreciated the AI’s interactive question format. “The question-based learning feels engaging, and the starter project it builds is simple but useful,” she says.
This structure ensures you don’t develop the wrong mental models — a known risk in fully constructivist or student-centered environments — while still giving you the freedom to explore.
Why learn when AI can build?
There are some projects that are well-suited for simply vibe coding, like making a personal HTML website or a single-use script to automate a one-time task. Tools like Lovable and v0 are suited exactly for these types of projects.
The longer your code needs to live, and the more complex your project becomes, the more you need to actually understand what you’re building. Joe Holmes, Codecademy Curriculum Developer in the AI and machine learning domain, uses the term “ignorance debt” to describe what happens when you don’t:
“It’s like tech debt squared. It’s much, much worse,” Joe says. “You don’t know what kind of code is coming out. You just are only looking at: Does this kind of generally appear to be what I asked for? You don’t know if there are security flaws. You don’t know if there are performance flaws. You don’t know if you’re leaking sensitive information. You don’t know how to fix anything.”
The tipping point comes down to two factors: complexity and time. If you’re developing software professionally, you’re legally responsible for the code you output. If you’re building something that will serve actual users, you need to be accountable for security, performance, and maintainability. And if your project will need updates or fixes over time (which most do) understanding your codebase becomes essential, not optional.
The good news? Learning doesn’t have to feel like eating your vegetables. “Kids hate veggies and broccoli because we don’t cook it well enough to make it tasty when we first introduce it to them,” says Nhi Pham, Codecademy Curriculum Developer. The same is true for teaching AI: “If you do it well, you’re inspiring people to have these very hygienic practices when working with AI,” she says.
That’s exactly what AI Builder is designed to do — make learning feel as immediate and rewarding as building, so you develop good habits from the start rather than building a lifelong aversion to understanding your own code.
Get started with the AI Builder
AI isn’t a replacement for learning, it’s a tool — and a powerful one when it comes to education. Our new AI Builder allows for “just‑in‑time learning that’s highly personalized,” Zoe says. Even the best teachers or bootcamps can’t deliver that for every learner, on every project, instantly. Perhaps the most exciting vision is how AI changes what a learning environment can be.
Zoe described it beautifully: “I imagine the AI Builder as a workspace… like having all your resources around you and an AI tutor in the background.”
That’s the shift: from learning before you build to learning while you build. We can’t wait to see what you create.
Why the Future of Learning Starts with Building
Coding has always served two purposes: the intrinsic drive to build something, and the practical path to a lucrative career. Even the most passionate code aficionados don’t dream of variables or syntax — they want to make a website, a tool, a game. For years, the career upside was impossible to ignore. You could land a stable SWE job, bootstrap your own app, or join a buzzy startup as a first hire.
Generative AI flipped the script. AI now handles the repetitive tasks that used to define entry-level developer roles. At the same time, the barrier to entry for coding and building is lower than ever — you can spin up a working prototype with just an idea and a natural language prompt.
This shift hasn’t eliminated the desire to code, but it’s changed what and who coding is for. If you’re not learning to land a junior dev role, you’re learning to build the thing you’ve been imagining, to add a technical skill to your existing career, or to understand the tools you’re already using at work. And here’s the catch: those goals all require understanding your code, not just having code that works.
At Codecademy, all of these changes excite us about the future of learning to code. We’re introducing the AI Builder, a new project-based learning tool that flips the script by teaching you how to work with AI-generated code from the start. Our approach brings together the immediacy of modern AI tools and the rigor of real instructional design.
Why we created the AI Builder
AI’s speed and efficiency often come with a tradeoff; you can get working code immediately, but you don’t really know what it’s giving you or why it’s built a certain way. Developers use the term “vibe coding” to describe this phenomenon — it’s fast, fun, but shallow; great for demos, less great for long-term skill-building.
If your goal is to understand what you’re building, generic AI output alone won’t get you there. And the more you push these tools into real-world complexity, “the harder it is for them to give you exactly what you want,” says Zoe Bachman, Head of Learning at Codecademy.
With the AI Builder you get an education along with the AI output. In the workspace, you can toggle between two tabs: Build, where you work directly with a project and can modify and change code in real time; and Learn, where you get a personalized learning roadmap that’s based on your project.
“We pair the experience of having a working app with a learning path that allows you to reverse engineer how it’s built, so you can deeply understand it and modify it confidently,” Zoe says. We’re calling our hybrid approach to learning-driven development “vibe learning” — it’s powered by AI guidance but rooted in learning science.
Build first; learn continuously
With AI Builder, you start with what you want to do: build the thing in your head. Whether that’s a habit tracker, a portfolio site, or the seed of a bigger idea, you don’t need to have prior coding knowledge to learn and build with the AI Builder. In other words, there are no pre-requisites for creation.
You create a prototype by typing what you’d like to create in natural language. The AI chatbot will ask a few clarifying questions about your needs and overall goal before generating the project. Once the project is created, you can use the chat function to continue describing what you want. (You’re also welcome to go right into the code and start making changes if you already know your way around!)
“It was fun to build something so quickly and be able to see the code and a learning plan for it,” says Grace Krishna, a Code Crew member who beta tested the AI Builder.
When you need clarity on what’s going on behind the scenes in your code, or you hit a wall with AI, that’s a great time to flip over to the Learn tab.
We’re calling our hybrid approach to learning-driven development ‘vibe learning’ — it’s powered by AI guidance but rooted in learning science.
Your project becomes the curriculum
Rather than teaching concepts in the abstract and hoping learners translate them later, AI Builder removes that translation tax entirely. “We’re showing you specifically your code from your project and helping you understand it,” Zoe says.
To build that personalized curriculum, the AI Builder breaks your project’s code into clear milestones and tasks. For each task, it generates an interactive learning loop, which is an activity designed to help you form a mental model of what your specific code is doing.
These loops help you understand the logic behind each part of your project, so you can confidently apply the same thinking to other sections, or even future projects. This approach also ensures everything you learn is directly relevant to what you’re making — so you don’t have to guess when you’ll ever use this.
Why this is vibe learning (not vibe coding)
A key misconception about AI‑assisted development is that it makes learning superficial. AI Builder challenges that by grounding the entire experience in learning science rather than simple code generation. Our entire system is intentionally designed for you to retain knowledge. So, while it might not feel like you’re taking a course, you’re absorbing key concepts just by interacting with AI-generated code.
A Socratic AI, not an answer-spitting chatbot
Our educational AI chatbot is designed to guide you toward an answer through an in-depth questioning approach that’s based on the Socratic method of teaching. Instead of spitting out shortcuts or answers like AI typically does, you get strategic nudges, hints, and questions that build durable mental models.
Research on AI in education shows that just providing an answer makes it harder for learners to retain the information on their own. Zoe compares the Socratic AI to “a personalized tutor, facilitating you acquiring more knowledge, so you’re not totally left on your own.” Our method encourages you to think critically so you really grasp the concepts and can continue to use them in the real world.
Learning loops with real instructional design
Behind the scenes, every learning loop in the Learn tab is built on proven frameworks like inductive learning and the 5E model, a popular STEM teaching framework that’s shorthand for engage, explore, explain, elaborate, and evaluate.
You’ll notice that the questions and exercises in the Learn tab feel different than the rest of our courses and paths, and that’s intentional. “The learning loops are designed very well — they get you there inductively,” Zoe says. They’re exploratory without being overwhelming, and evaluative without feeling like tests.
Negar Vahid, a beta tester for the AI Builder appreciated the AI’s interactive question format. “The question-based learning feels engaging, and the starter project it builds is simple but useful,” she says.
This structure ensures you don’t develop the wrong mental models — a known risk in fully constructivist or student-centered environments — while still giving you the freedom to explore.
Why learn when AI can build?
There are some projects that are well-suited for simply vibe coding, like making a personal HTML website or a single-use script to automate a one-time task. Tools like Lovable and v0 are suited exactly for these types of projects.
The longer your code needs to live, and the more complex your project becomes, the more you need to actually understand what you’re building. Joe Holmes, Codecademy Curriculum Developer in the AI and machine learning domain, uses the term “ignorance debt” to describe what happens when you don’t:
“It’s like tech debt squared. It’s much, much worse,” Joe says. “You don’t know what kind of code is coming out. You just are only looking at: Does this kind of generally appear to be what I asked for? You don’t know if there are security flaws. You don’t know if there are performance flaws. You don’t know if you’re leaking sensitive information. You don’t know how to fix anything.”
The tipping point comes down to two factors: complexity and time. If you’re developing software professionally, you’re legally responsible for the code you output. If you’re building something that will serve actual users, you need to be accountable for security, performance, and maintainability. And if your project will need updates or fixes over time (which most do) understanding your codebase becomes essential, not optional.
The good news? Learning doesn’t have to feel like eating your vegetables. “Kids hate veggies and broccoli because we don’t cook it well enough to make it tasty when we first introduce it to them,” says Nhi Pham, Codecademy Curriculum Developer. The same is true for teaching AI: “If you do it well, you’re inspiring people to have these very hygienic practices when working with AI,” she says.
That’s exactly what AI Builder is designed to do — make learning feel as immediate and rewarding as building, so you develop good habits from the start rather than building a lifelong aversion to understanding your own code.
Get started with the AI Builder
AI isn’t a replacement for learning, it’s a tool — and a powerful one when it comes to education. Our new AI Builder allows for “just‑in‑time learning that’s highly personalized,” Zoe says. Even the best teachers or bootcamps can’t deliver that for every learner, on every project, instantly. Perhaps the most exciting vision is how AI changes what a learning environment can be.
Zoe described it beautifully: “I imagine the AI Builder as a workspace… like having all your resources around you and an AI tutor in the background.”
That’s the shift: from learning before you build to learning while you build. We can’t wait to see what you create.
