Build and share two applications—a website performance analyzer and a voting app—while using an AI coding agent to debug, customize, and strengthen your coding skills.
Beginner1h34m
Vibe Coding 101 with Replit
Instructors: Michele Catasta, Matt Palmer
Earn an accomplishment with PRO · Updated Oct 29, 2025
- Beginner
- 1h34m
- 7 Video Lessons
- 1 Graded Assignment PRO
- Earn an accomplishment with PRO
- Updated Oct 29, 2025
- Instructors: Michele Catasta, Matt Palmer
Replit- Learn more aboutMembership PRO Plan
What you'll learn
Learn the principles of agentic code development and skills to effectively build, host, and share your apps with Replit coding agents and assistants.
Use product requirement documents, wireframes, and good prompting practices to prototype, debug, and iterate your applications.
Course recap
PROThis course teaches "vibe coding" -- building production-ready web applications using AI coding agents without writing code manually. Using Replit's Agent and Assistant tools, students learn to describe what they want in natural language and let the AI build full-stack applications with persistent storage, deployment, and custom URLs.
Concept map
Key concepts
- Vibe codingBuilding applications by describing desired functionality to AI agents rather than writing code manually
- Logical hierarchy of thoughtMoving from "what is the problem?" (logical thought) to "how do I solve it?" (procedural thought) to "how do I instruct the AI?" (implementation)
- CheckpointsVersion control and incremental building; chunking work into MVPs and features
- Context managementProviding images, links, data, and detailed descriptions to help AI agents understand requirements
- AI debuggingMethodical, thorough investigation of errors using the AI assistant to understand application behavior
Lesson highlights
- 1.Introduction — Five core skills: thinking, frameworks, checkpoints, debugging, context
- 2.Thinking and Frameworks — Understanding the problem domain; choosing appropriate tools and frameworks
- 3.Building App 1 — Creating a game application with Replit Agent
- 4.Building App 2 — National parks ranking system with persistent storage
- 5.Debugging with AI — Systematic error investigation and resolution
- 6.Deployment — Publishing to custom URLs with full-stack infrastructure
- 7.Next Steps and Best Practices — Recap of iterative building pattern; continuing the vibe coding journey
About this course
Learn to build and host applications with an AI agent in Vibe Coding 101 with Replit, built in partnership with Replit and taught by Michele Catasta, President, and Matt Palmer, Head of Developer Relations.
Coding agents are changing how we write code. “Vibe coding” is a growing practice where you lean into letting a coding agent do most of the heavy lifting while you focus on the architecture and features of your application. But effective vibe coding isn’t just about one-shot prompting, accepting all recommendations, and hoping for the best. It involves structuring your work, refining your prompts, and using frameworks that lead to cleaner, more efficient code.
In this course, you’ll use Replit’s cloud environment— with an integrated code editor, package manager, and deployment tools—to build and deploy two web applications with the help of an AI coding agent. Along the way, you’ll learn strategies for working effectively with agents and improve your development skills in the process.
In detail, you’ll:
- Understand principles of agentic code development such as being precise, giving agents one task at a time, making prompts specific, keeping projects tidy, starting with fresh sessions for each new feature, and adopting patience while debugging.
- Learn how to get started with Replit, and understand fundamental concepts behind effective AI collaboration including a “five-skill framework” in vibe coding of thinking, using frameworks, checkpoints, debugging, and providing context.
- Create a product requirement document (PRD) and wireframe for your agent to build a prototype of a website performance analyzer.
- Use the agent to make your prototype more visually appealing, switch to assistant mode to customize your applications with screenshots and prompts, and deploy your application so others can access it online.
- Build a head-to-head national park ranking app, from a sample dataset, with voting capabilities and persistent data storage.
- Refine your app by integrating a complete dataset, and ask the assistant to recap and explain what it built to find room for improvement and reinforce your learning.
By the end of this course, you’ll have a solid foundation in building with coding agents—and a process you can use to keep vibe coding effectively.
Who should join?
Anyone can join! It’s helpful to have some coding experience and some background in prompting LLMs.
To complete the course you will need to signup for a free Replit account here.
Course Outline
7 Lessons・0 Code Examples- IntroductionVideo・3m
- Principles of Agentic Code DevelopmentVideo・18m
- Planning and Building an SEO AnalyzerVideo・23m
- Implementing SEO Analysis FeaturesVideo・12m
- Planning and Building a Voting AppVideo・26m
- Enhancing the National Parks Voting AppVideo・7m
- Next steps and Best PracticesVideo・4m
- Quiz
Graded・Quiz
・10m
Elevate your learning experience with Pro
Upgrade to Pro and gain unlimited accomplishments on your resume
Instructors
Course access is free for a limited time during the DeepLearning.AI learning platform beta!
Want to learn more about Generative AI?
Keep learning with updates on curated AI news, courses, and events, as well as Andrew’s thoughts from DeepLearning.AI!