> AI agents: For documentation discovery and navigation, see [llms.txt](/llms.txt). # Prompt examples This article provides example prompts for chat in Visual Studio Code across different scenarios and agents. Use these examples as inspiration to craft effective prompts for your own development tasks. If you are new to using chat in VS Code, learn more about [getting started with chat](/docs/chat/chat-overview.md) or review [best practices for prompt crafting](/docs/agents/best-practices.md).
Follow a hands-on tutorial to build an app with AI agents in VS Code. * [Start agentic coding tutorial](/docs/agents/agents-tutorial.md)
## General coding and technology questions Use the **Ask** agent to get quick answers about coding concepts, technology topics, and general programming questions. ```prompt-ask What is a linked list? ``` ```prompt-ask Provide 3 ways to implement a search feature in React. ``` ```prompt-ask Explain the difference between async/await and promises. ``` ## Understanding and exploring your codebase Use the **Ask** agent with `#codebase` to understand how your project works, locate specific functionality, or explore code relationships. For a guided investigation with source references and verification steps, see [Explore a codebase with an agent](/docs/agents/guides/explore-a-codebase.md). ```prompt-ask Explain how authentication works in #codebase ``` ```prompt-ask Where is the database connection string configured? #codebase ``` ```prompt-ask How do I build this #codebase? ``` ```prompt-ask Which testing framework is used for #calculator.test.js? ``` ## Code generation and editing Use **Agent** for multi-file creation and **inline chat** (`kb(inlinechat.start)`) for targeted, in-place edits. For complete workflows in an existing project, see [Add a feature](/docs/agents/guides/add-a-feature.md) and [Refactor without changing behavior](/docs/agents/guides/refactor-safely.md). ```prompt Add a login button and style it based on #styles.css ``` ```prompt Create a meal-planning web app using React and Node.js ``` ```prompt Refactor this code to use async/await ``` ## Testing and quality assurance Use **Agent** to generate tests or fix failing tests. ```prompt Add unit tests for the user service. ``` ```prompt Fix the failing tests #testFailure ``` ## Debugging and fixing issues Use **Agent** for fixing issues across files, or **Ask** to understand the root cause first. ```prompt Fix the issues in #problems ``` ```prompt Why is this function returning undefined? ``` ## Working with source control Use chat to work with your pending changes and generate release documentation. ```prompt Summarize the #changes ``` ```prompt Generate release notes based on the #changes ``` ## Working with external resources Use `#fetch` to reference content from the web or use the GitHub MCP server to search for code examples in public GitHub repositories. ```prompt How do I use the 'useState' hook in react 18? #fetch https://18.react.dev/reference/react/useState#usage ``` ```prompt Build an API endpoint to fetch address info, use the template from GitHub repo contoso/api-templates ``` ```prompt What are the top #extensions for this workspace? ``` ## Terminal and command-line tasks Use [terminal inline chat](/docs/chat/inline-chat.md#use-terminal-inline-chat) to get help with shell commands and terminal operations. ```prompt How do I install npm packages? ``` ```prompt List the top 5 largest files in the src directory ``` ```prompt undo the last git commit ``` ## Working with Jupyter notebooks Use **Agent** to create, edit, and work with Jupyter notebooks. ```prompt /newNotebook use pandas and seaborn to read and visualize the titanic dataset. Show key information from the dataset. ``` ```prompt Create a notebook to read data from #housing.csv and plot the distribution of prices ``` ```prompt Make sure the data is cleaned before visualizing and processing it ``` ```prompt Show the correlation between different features in the dataset ``` ## Multi-turn conversation examples Chat supports follow-up prompts within the same session. Use multi-turn conversations to iterate on results and refine the AI's output. **First prompt:** ```prompt Create a REST API with Express.js that has endpoints for users and products ``` **Follow-up prompts:** ```prompt Add input validation and error handling to both endpoints ``` ```prompt Now add unit tests for the validation logic ``` By building on earlier responses, the AI maintains context from the previous steps and generates more coherent code. ## Tips for crafting effective prompts * **Be specific**: Include details about what you want to accomplish, the technologies to use, and the expected output format. * **Add context**: Use #-mentions to reference files, symbols, or context variables like `#codebase`, `#changes`, or `#problems`. * **Iterate**: Start with a simple prompt and refine it based on the response. Ask follow-up questions to improve the results. * **Break down complex tasks**: Instead of asking for everything at once, break large tasks into smaller, manageable steps. Learn more about [best practices for crafting prompts](/docs/agents/best-practices.md) and [adding context to your prompts](/docs/chat/copilot-chat-context.md). ## Related resources * [Chat overview](/docs/chat/chat-overview.md) * [Add context to your chat prompt](/docs/chat/copilot-chat-context.md) * [Inline chat](/docs/chat/inline-chat.md) * [Copilot Chat Cookbook](https://docs.github.com/en/copilot/example-prompts-for-github-copilot-chat) in the GitHub documentation