GitHub Copilot CLI Challenge | Solving Lunch Indecision | Building a Restaurant Slot Picker with GitHub Copilot CLI
Source: Dev.to
What I Built
As a junior frontend engineer who recently graduated from college, I found that the hardest decision I make every day isn’t about code architecture—it’s “What should I eat for lunch or dinner?”
I built the Restaurant Slot Picker, a fun and interactive web application designed to solve daily “choice paralysis” when it comes to food. It identifies your current location, finds nearby restaurants, and presents them in a slot‑machine interface. With a single click, it randomly selects three options for you. Clicking on a card takes you directly to Google Maps for navigation.
The three options are selected independently, so you might get three identical results—if that happens, you’re lucky and you must try that restaurant!
Demo
- Live Demo:
- Source Code:
How it Works
When you first visit the page, you will see this interface:
- Click the “Spin the Slot Machine” button.
- After a few seconds, the app reveals three dining options:
- Pick the one that looks best. Clicking the card navigates you directly to Google Maps.
My Experience with GitHub Copilot CLI
Before this challenge, I exclusively used GitHub Copilot Chat within VS Code. Although I knew Copilot had a CLI, I had never tried it. This challenge gave me the push I needed to explore it.
The Learning Curve
I started using the Copilot CLI with nervousness because it can execute operations on my project. Not being fully familiar with CLI commands, I verified every action it proposed. This “forced learning” turned into a benefit—I had to understand various command‑line instructions before approving them.
From “Micromanager” to “Boss”
Progress was initially slow as I was cautious and didn’t fully trust the tool. Once I built that trust and let it execute commands autonomously, development speed skyrocketed. It could build features automatically while I watched YouTube, occasionally checking results or providing new specifications. It felt incredibly “chill”—like I was a boss chatting with a developer and delegating tasks.
Beyond Code: APIs and Deployment
Copilot CLI proved useful beyond writing logic. It guided me through infrastructure tasks such as applying for the Google Maps API and deploying the project to Vercel. Instead of wading through lengthy documentation, it generated clear, step‑by‑step instructions, allowing me to complete these configurations smoothly.
Finding the Balance: Direct Agent vs. Strict Specs
For complex features, the agent sometimes misunderstood my intent. I researched better ways to converse with AI agents and experimented with strict project specifications (spec‑driven development). While this approach can lead to over‑engineering—producing unnecessary tests or functions—it offers more control for larger tasks. The direct Agent mode remains faster and easier for smaller tasks. Knowing when to use each strategy is key.
Conclusion
I also tried the Copilot delegate features, which let the agent run in the cloud and create PRs for review. It makes me feel like I have the capabilities of a senior engineer, even though I just graduated!
Overall, the tool is incredibly cool. The biggest takeaway is that communicating with AI is a skill in itself; if the AI doesn’t meet expectations, my description likely needs improvement. I can’t wait to see what else I can build with it.