fbpx
Home Blog Page 130

Why the Future of Learning Starts with Building

0

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.  

Switch to Learn for behind-the-scenes insights and your personalized roadmap.

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.  

Rework your prototype in real time with the help of AI.

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

0

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.  

Switch to Learn for behind-the-scenes insights and your personalized roadmap.

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.  

Rework your prototype in real time with the help of AI.

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

0

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.  

Switch to Learn for behind-the-scenes insights and your personalized roadmap.

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.  

Rework your prototype in real time with the help of AI.

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

0

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.  

Switch to Learn for behind-the-scenes insights and your personalized roadmap.

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.  

Rework your prototype in real time with the help of AI.

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. 

How Do Secondary Students Study, and Are Their Choices Related to Their Beliefs in Achievement?

0
How Do Secondary Students Study, and Are Their Choices Related to Their Beliefs in Achievement?

*For the uninitiated, a Toniebox is a little speaker. They work with special figurines, called Tonies. The kids put a Tonie on the box and it starts playing whatever is loaded. Some read stories, some play music, and some are like little screen-free “shows” that teach the kids about concepts and sing. By the way, this is not a paid advertisement; we don’t do that on our site! My family just really loves our Toniebox.

Coach Hippo is all about helping develop healthy habits, like exercising, eating a variety of whole foods, getting enough rest, and importantly, believing in yourself. The result is that my daughter is constantly asking us to “Do Gym Class” with her, and runs around the house signing songs with lyrics like, “the best I can be” and “I am a super star, today I will shine!!”.

I love that she is developing confidence, and that this is part of what she is learning as healthy habits. I have been thinking a lot about mindset, motivation, and self-efficacy lately, with relation to my daughter and also my college students.

This brings me to the point of today’s blog, a paper by Héctor Ruiz-Martín, Fermando Blanco, and Marta Ferrero examined how secondary students report studying, and the associations these choices have with students’ beliefs in their own abilities (1).

There have been a number of surveys conducted over the last 20 years asking what students report doing when they study, and attempting to link those results to student achievement. The bulk of this work has been conducted with students in higher education, and typically looks at academic achievement and students’ predictions about how well the strategies will help them. This 2024 paper by Ruiz-Martín and colleagues seems unique to me because they studied younger students (i.e., secondary) and their self-efficacy. Understanding student attitudes towards various strategies, and how engaging in them affects their belief in their own ability to achieve (i.e., self-efficacy), mindset, and anxiety related to testing is, I believe, essential if we hope to promote evidence-based study strategies and see students adopt them.

The researchers collected data from students in grades 7 through 12 from a number of schools across Catalonia (the northeastern region of Spain). Ultimately, their final sample was over 3,400 students. The researchers administered two surveys to the students.

The first survey contained questions about the study strategies that students use, drawing heavily from the previous research in this area. The students indicated how often they engaged in the various study behaviors described in the study, such as retrieval practice, various forms of elaboration, rereading, highlighting, copying, etc.

The second survey assessed the students’ beliefs and attitudes toward learning. The scales assessed:

  • self-efficacy—students’ confidence in their ability to achieve in school,

  • learning goals—students’ interests in learning at school,

  • performance goals—students’ interest in getting good grades,

  • control beliefs—students’ beliefs that they can control factors related to their success

  • growth mindset—students’ beliefs that their abilities could be improved

  • examination anxiety—stress and anxiety associated with tests

Finally, the researchers gathered information from the schools about the students’ final grades.

The researchers collected a lot of data, and so there are a lot of important findings in their paper. I will focus here on the things that I found to be the most interesting.

Reported Strategy Use

Most students, nearly 78%, reported never being taught how to study.

Unsurprisingly, “rote learning” was one of the most frequently reported approaches to studying, while retrieval practice was one of the least frequently used strategies (at least as reported by these students). When retrieval practice was reported being used, it was most often associated with rehearsing information after reading it. Spaced practice was also a low-prevalence strategy in their data.

Effective Strategy Use and Achievement

Some were! There were correlations between retrieval practice use and higher grades, but the correlations were low (~.20, for example). Spacing was not associated with higher grades. Of course, we know that long-term learning and getting good grades are not one in the same. And, importantly, the association between evidence-based strategies, such as retrieval practice and elaboration, and achievement were higher than with the low utility strategies, such as highlighting or copying notes. The authors keenly point out that while correlation does not mean causation, the lack of correlation can imply lack of causation. The lack of correlation between highlighting and copying and achievement suggests that these strategies do not cause changes in achievement.

Beliefs and Attitudes Towards Learning

The data suggested students viewed their grades as a higher priority than learning. More students had a growth mindset than a fixed mindset. These two results may seem contradictory given the theory, and the authors discuss this at length for those interested.

Most interesting to me, effective, evidence-based strategies (retrieval practice, elaboration, etc.) had a greater association with positive attitudes towards learning than the low-utility strategies (highlighting, rereading, copying, etc.). In other words, the students using effective, evidence-based strategies were more likely to have higher self efficacy, for example, compared to those that did not report using the effective strategies.

The low utility strategies, like rereading, copying, etc., did not correlate with self-efficacy. This means that use of these strategies is distributed among those with higher and lower self-efficacy, suggesting these strategies do not have an effect on self-efficacy.

The authors conclude that effective, evidence based strategies were largely the ones that were associated with student achievement and positive attitudes towards learning.

Why the Future of Learning Starts with Building

0

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.  

Switch to Learn for behind-the-scenes insights and your personalized roadmap.

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.  

Rework your prototype in real time with the help of AI.

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

0

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.  

Switch to Learn for behind-the-scenes insights and your personalized roadmap.

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.  

Rework your prototype in real time with the help of AI.

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

0

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.  

Switch to Learn for behind-the-scenes insights and your personalized roadmap.

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.  

Rework your prototype in real time with the help of AI.

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

0

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.  

Switch to Learn for behind-the-scenes insights and your personalized roadmap.

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.  

Rework your prototype in real time with the help of AI.

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

0

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.  

Switch to Learn for behind-the-scenes insights and your personalized roadmap.

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.  

Rework your prototype in real time with the help of AI.

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.