
**zpl.tools** is a fast, privacy-first parser and renderer for ZPL — the Zebra Programming Language behind virtually every shipping and retail label.

The pain it solves: a single wholesale order can ship as **thousands of boxes**, each with its own retail or carton label. When you need to *preview* those labels before they print, the existing tools fall down — they're rate-limited, paged, paid, or they want you to upload label data with real customer details to someone else's server. None of them comfortably render a whole order's worth of labels at once.

zpl.tools does. It renders ZPL to pixel-accurate images instantly in the browser — one label or thousands — with no Zebra printer, no API limits, and no round-trip to a third party, so sensitive label data never leaves your machine. The core is written in Rust and built to run anywhere: an online viewer today, with desktop apps and SDKs (Rust, JavaScript, native) on the way.

Carrier labels (FedEx, UPS, DHL) work too — but the thing no other tool does well is previewing retail and carton labels at the scale a real order demands.

Currently in beta, with a full launch planned for 2026.

[Try the online viewer →](https://zpl.tools/online-viewer)



**bytiq.cz** pulls property listings from all the major Czech real-estate portals into a single, queryable analytical view.

I built it for myself. A partner and I were actively investing and wanted to rank offers by *our* parameters — above all **price per m² against the neighborhood average** — instead of whatever order each portal happened to show. No existing tool sliced the market that way, and the data was scattered across portals that never compare against each other.

- **Scraping:** Node.js scrapers across the major Czech property-listing platforms.
- **Application data:** PostgreSQL.
- **Analytics:** Snowflake on top, powering the analytical layer.

It's the personal version of a pattern I keep applying at work: scrape disparate external sources, normalize them, and surface the result as a queryable analytical layer with a usable UX on top. In active use since 2025.


Products I own

Hardware, firmware and signal work — C, custom PCBs, RF.


A hardware project I built to learn by doing: LED lighting that reacts to music, designed from the board up rather than assembled from a kit.

I built the whole signal path myself:
- a custom **ATmega32** board doing the driving and timing
- analog **amplification** for the incoming audio, fed through an **ADC** so the microcontroller could actually read the waveform
- the logic to turn that signal into light moving in time with the sound

Most of what I understand about the firmware/electronics boundary I picked up on projects like this one — a soldering iron, a datasheet, and a circuit that does nothing until, suddenly, it does. I later built a wireless companion to it, controlling the strips over RF instead of a wire.

## Final product
![led strips](/projects/optimized/led_strips_3.JPG)



A local company ran a machine that extruded filament for 3D printers, and they needed two things they didn't have: a way to know how far each spool drifted from spec, and a way to trace any spool back to the run that produced it. I built the system that did both, end to end — from the sensor on the line down to the database.

## The measurements
A prebuilt measuring unit sat on the production line and read the filament as it was wound. I wired it to a Raspberry Pi over a serial interface, and the Pi streamed every reading into a MySQL server — so deviations were captured continuously instead of spot-checked by hand once a shift.

## Spool tracking
The spooling itself ran on the company's own custom mechanism, so I left that alone and tapped into it: a pressure switch that triggered the moment a spool filled up. That signal told the Pi to close the spool out, assign it a serial number, and print a label on a connected printer. Every finished spool came off the line already tagged and already in the database.

It was some of my earliest hands-on work tying hardware straight to software — a sensor, a microcontroller, a database, and a printer all made to agree with each other. That thread, making the physical and digital layers line up, kept resurfacing later: in the NFC payment tokens at NFCtron, and in my own hardware side-projects since.


Close to the metal

Production systems built for and with other people.


**Awincado** was a heavily customized e-commerce store. I ran the build with a small team — a backend and a frontend engineer reporting to me — and owned the product and delivery side myself.

# The technical side
Technically it was a set of extensions on top of the [Vendure](https://vendure.io) e-commerce platform, plus a custom storefront:
- contest / event mechanics
- coupon-code handling with automated email fulfillment
- [Zalando](https://zalando.com) integration
- GoPay payment integration
- PayU payment integration
- [Pohoda](https://pohoda.cz) accounting integration



# Project
A voting platform for the judges of Miss Czech Republic, built for the 2021 grand finale. During the live show, judges would score the contestants from iPads in real time and the results would tally instantly. The same tool managed candidate data and tracking through the earlier casting rounds, and was designed to be reused season over season.

The platform was delivered complete, tested, and fully functional, ready for the live broadcast.



**ISITIN.CLOUD** answers one question: paste in any website and it tells you which cloud provider actually hosts it.

I built it out of curiosity. The big providers all publish the IP ranges they own — AWS, Google, Azure, and the rest — so "who hosts this site?" is a question you can answer mechanically, if you bother to line the data up. Nobody had turned that into a one-box lookup, so I did.

The mechanism is deliberately small:
- pull each provider's published IP ranges from their public APIs
- resolve the site's IPs and match them against those ranges

The whole thing runs serverless on AWS Lambda — no box to keep alive, just a function that wakes up when someone asks. The kind of weekend project that pays off more as a sharpening exercise than as a product, but it does exactly what it says on the tin.



NFCtron Plus gives event organizers and merchants real-time access to their sales data — the numbers they previously had to request from us by hand.

It also turned event setup into self-serve: building the product catalog and configuring an event used to be a manual job for support or developers, and NFCtron Plus put that directly in the organizers' hands.



bitticket.cz was a platform for booking and validating event tickets, through either a mobile app or a desktop web app.

It was my first real project used by real people. We were organizing a lot of events at the time and didn't want to hand ~15% of every sale to the incumbent ticketing platforms, so I built our own — reservations, ticketing, and entrance validation. It worked: it ran across several high schools and handled on the order of a million CZK in ticket sales, saving roughly that 15% in fees.

I had no idea about the risks I was taking on at the time — each merchant plugged in their own GoPay credentials and we only facilitated the booking on the technical side — but it shipped, it got used, and it was a success.


Projects

Products I own

zpl.tools

bytiq.cz

Close to the metal

LED microcontroller

Filament quality measurement

Platforms and integrations

Awincado

Miss Czech Republic

ISITIN.CLOUD

NFCtron Plus

bitticket.cz