Use Copilot to scaffold a full-stack app
They let GitHub Copilot start a new full-stack app, then kept fixing setup issues until the React interface was styled and usable.
- What they did
- They used GitHub Copilot agent mode to kick off a fresh project that included a web client, backend code, and a database, with React, TypeScript, Tailwind, ShadCN/UI, Python, Clojure, and PostgreSQL in the stack. For every attempt, they handed over three inputs: a project brief, a task list, and an instructions file for Copilot. They then watched the terminal closely, corrected bad file paths and Windows/Linux command mismatches, and kept editing the instructions after each run.
- How it went
- Claude 3.7 Sonnet was the most persistent when errors appeared, but the first attempts still broke during the React, Tailwind v4, and ShadCN setup. After another Claude run and clearer guidance, they ended up with React components that were both styled and working.
- Tips
- If you try this, plan to supervise the installation steps instead of leaving them unattended. It also helps to stop for approval before any install, config change, or other action that could be hard to undo.
Try it yourself with GitHub Copilot
In agent mode, help me start a new full-stack app for [describe the app]. Use [frontend stack] for the user interface and [backend/database stack] for the server side. Begin by laying out the project files, then make sure it runs locally, then build the visible parts of the app for [key pages or features]. I’ll provide a project brief, a task list, and an instructions file—follow those closely. If anything fails, try to repair it yourself first, but pause and ask me before you install extra tools, change configuration outside the project directory, or take any irreversible action.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Run Copilot CLI in loops and split multi-part work
Daniel Ward used GitHub Copilot’s autopilot and /fleet features to finish larger jobs and divide separate chunks across parallel agents.
Build an anonymous board for AI hopes and worries
They used Claude Code to create a site where people can post anonymously, with one model sorting entries and another finding themes.
Use Copilot CLI subagents for parallel terminal work
A commenter used GitHub Copilot CLI to split repo work across multiple subagents, run commands in parallel, and review the results live.
Make a first app with Replit and Claude
A commenter used Replit’s agent with Claude Sonnet to assemble an app in about five minutes, despite having no real coding experience.
Update a codebase with Copilot in chat and agent mode
A developer used GitHub Copilot to make code changes and preferred the CLI’s autopilot workflow and todo list.
Set up layered agent code reviews
A team had Claude Code write most code, then used multiple review layers to catch bugs before merge.