Use Claude code to explore, develop, test, refactor, and debug codebases.
We'd like to know you better so we can create more relevant courses. What do you do for work?
Instructor: Elie Schoppik
Use Claude code to explore, develop, test, refactor, and debug codebases.
Extend the capabilities of Claude Code with MCP servers such as Playwright and Figma MCP servers.
Apply Claude Code best practices to three projects: exploring and developing the codebase of a RAG chatbot, refactoring a Jupyter notebook for e-commerce data and transforming it into a dashboard, and building a web app from a Figma mockup.
Learn the best practices for agentic coding with Claude Code in this new short course, Claude Code: A Highly Agentic Coding Assistant, built in partnership with Anthropic, and taught by Elie Schoppik, Head of Technical Education.
AI coding assistants have evolved rapidly, from tools that help with occasional coding questions and code completion to tools that can autonomously generate code. Claude Code pushed the degree of autonomy by acting as a highly agentic assistant that can plan, execute, and improve code with minimal human input, for more than a few minutes. You and your teammates can now run multiple instances of Claude code and work in parallel on different parts of the codebase. However, coordinating all this involves a set of best practices that can significantly boost your productivity.
In this course, youâll learn best practices for using Claude Code to improve your coding workflow. Youâll learn key tips on how to provide Claude Code with clear context, such as specifying the relevant files, clearly defining the features and functionality, and connecting Claude Code to MCP servers.
Youâll apply these best practices to three examples: exploring a RAG chatbot codebase, analyzing ecommerce data in a Jupyter notebook, and creating a web app based on a Figma mockup.
In detail, using Claude Code, youâll:
By the end of this course, youâll have a set of best practices you can apply to speed up and improve your coding workflow.
This course is ideal for anyone who wants to explore how AI coding assistant tools like Claude Code can enhance their development process. Whether youâre building applications, debugging code, or exploring unfamiliar codebases, youâll gain practical skills to work more efficiently with AI-assisted workflows. You can make the best of the course if youâre familiar with Python and Git.
Introduction
What is Claude Code?
Course Notes
Setup & Codebase Understanding
Adding Features
Testing, Error Debugging and Code Refactoring
Adding Multiple Features Simultaneously
Exploring Github Integration & Hooks
Refactoring a Jupyter Notebook & Creating a Dashboard
Creating Web App based on a Figma Mockup
Conclusion
Prompts & Summaries of Lessons
Course access is free for a limited time during the DeepLearning.AI learning platform beta!
Keep learning with updates on curated AI news, courses, and events, as well as Andrewâs thoughts from DeepLearning.AI!