Forem: Ondřej Šimanovský

GitHub Copilot CLI Challenge - estazka.cz

Ondřej Šimanovský — Sun, 15 Feb 2026 10:54:42 +0000

This is a submission for the GitHub Copilot CLI Challenge

What I Built

I built an app called eStazka. It’s a passion project designed to help my dad’s trucking business escape the paperwork. Less time shuffling papers, more time actually running the business.

Basically, it handles everything a transport company needs: transport docs ("stazka"), vehicle management, fleet tracking, and inventory. I also hooked it up to the Czech invoicing service Fakturoid, so invoices can be generated automatically from transport documents.

On top of that, it keeps an eye on vehicle status, service history, and those annoying mandatory inspections (STK).

Demo

Try it here: eStazka.cz

Demo accounts

Go ahead and log in with these credentials to see how it works:

Owner account:

Username: novak@autodoprava-novak.cz
Password: password

Driver account:

Username: vesely@autodoprava-novak.cz
Password: password

My Experience with GitHub Copilot CLI

I’ve used the Copilot extension in VS Code before, but diving into the CLI for this challenge was a whole new experience.

I didn't write a single line of code manually.
The entire app was generated 100% via the GitHub Copilot CLI.

The "Zero-Code"

I tried this setup

The Setup: I wrote up a design doc and an app description, then fed it to the Copilot CLI to analyze and set the instructions.
The Plan: I lived in Plan Mode. I listed out all the requirements and features I wanted directly in the CLI.
The Blueprint: Once I dumped my ideas in, the CLI analyzed everything and generated a .md file for every single task in a todo folder. Think of them as AI-generated "Task Briefs."
The Build: I switched over to Normal Mode and told it to get to work.
The Loop: Copilot CLI just went through the todo folder. It implemented a feature, ran the tests, committed the changes, and moved on to the next one.

Breaking the dev process down into these micro-tasks allowed the AI to handle the heavy lifting one step at a time.

It was honestly a really fun experiment to see just how powerful these tools have become. I still love writing code myself (and I’m not stopping anytime soon), but having AI as a co-pilot—or in this case, the pilot—is something.

The AI Stack

I used a mix of models to get this done:

Gemini 3 Pro & Claude Sonnet 4.5: These handled the creative stuff—copywriting and UI design.
Claude Opus 4.5 & GPT 5.3 Codex: These were the workhorses for the actual feature implementation.

I was constantly toggling between Plan and Normal mode. Honestly, having that separation between "strategizing" and "executing" made the whole workflow smooth.

I built myself a Portfolio to showcase my work

Ondřej Šimanovský — Wed, 21 Jan 2026 19:47:41 +0000

This is a submission for the New Year, New You Portfolio Challenge Presented by Google AI

About Me

Hi, I'm Ondra, a 31-year-old software/web developer from the Czech Republic. I currently work full-time as a developer and recently started freelancing on the side. I built this portfolio to showcase my skills and projects while attracting new clients. As someone passionate about clean code and modern web technologies, I wanted my portfolio to reflect both my technical abilities and attention to detail.

Portfolio

(Note: Also deployed to Google Cloud Run with required label: --labels dev-tutorial=devnewyear2026)

How I Built It

My portfolio is built with a modern tech stack focused on performance, SEO, and maintainability:

Tech Stack

Frontend: Astro 5 with TypeScript - chosen for its excellent performance, SEO capabilities, and zero-JS-by-default approach
CMS: Payload 3 - a headless CMS to manage content on the website.
Styling: Tailwind CSS
Deployment: Google Cloud Run
AI Assistant: Google's Antigravity IDE, Gemini 3 Pro and Nano Banana for some images - invaluable for development assistance

Google AI Tools

I used Antigravity throughout the development process and AI Studio:

Animation Implementation: Antigravity helped me create smooth, performant scroll animations and transitions
Localization: Set up a complete i18n supporting English and Czech, making my portfolio accessible
SEO Optimization: Generated proper meta tags, structured data, and canonical URLs to ensure search engine visibility
Content Shaping: Improved my portfolio copywritting, project descriptions, and technical writing to be clear and engaging
Deployment: Gemini helped me with failing deployments. I have to change the output from static to server.

What I'm Most Proud Of

Performance: Achieved excellent Lighthouse scores. Using Astro image optimization
Bilingual Support: Implemented a complete localization system that seamlessly switches between English and Czech, making my services accessible to both local Czech clients and international opportunities
Smooth Animations: Created engaging scroll animations and transitions that enhance the user experience without sacrificing performance
Google Cloud Integration: Successfully deployed a containerized application to Cloud Run, demonstrating proficiency with modern cloud infrastructure

The portfolio represents not just my work, but also my approach to development: clean code, modern technologies, attention to detail, and a focus on user experience.

Live Site: www.justondra.dev

Tech Stack: Astro 5, Payload 3, TypeScript, Tailwind CSS, Google Cloud Run

Stream discovery - find a streamer

Ondřej Šimanovský — Wed, 19 Jul 2023 20:49:43 +0000

What I built

Streamer discovery is web app to discover, create and rate twitch streamer. Guest users can only search streamer. Logged in users can create new streamer and rate existing one.

Category Submission:

Best Overall Project
Most Visually Pleasing
Most Technical Impressive
Best Project built using Supabase as the main data provider for the refine app.
Best Project built using Material UI as the main UI framework for the refine app.

App Link

The project has been deployed with Vercel and can be found at the following link: Stream-discovery

Screenshots

Main page

Login page

Register page

Create new streamer

Description

Stream discovery is a web app for people who likes watching streams.
This app helps find a new streamer.
People can create account and then add new streamers and rate existing.
Guest users can only see and filter curretly added streamers.

Link to Source Code

The source code for the project can be found on GitHub at the following repository: GitHub Repo

Permissive License

The project is licensed under the MIT.

Background (What made you decide to build this particular app? What inspired you?)

I decided to build this app beacause nowadays is pretty popular the watch some people streaming things that they like.
I wanted to make app for people to easily find new streamers.
They can choose streamers based on rating from other users.

How I built it (How did you utilize refine? Did you learn something new along the way? Pick up a new skill?)

This Project is built using the following resources:

I definitely learn more about Next.js and discovered Refine which looks nice and good choice for my project.
I also learn how to work with Supabase which is also great tool that simplified so many things. And more importantly I learned how to work a use documentation of new tech tools.

Additional Resources/Info

I would love to continue in developing this app and add new features.
Something I have in mind:

Add fetch directly to twitch.tv to fetch data for particular streamer handle
Add add a comment for logged in users
Read comments for guest users.