Mentoring Tomorrow's AI Developers

  • How to Track QR Campaigns Before Cookie Consent with Cloudflare Workers and GA4 Measurement Protocol

    How to Track QR Campaigns Before Cookie Consent with Cloudflare Workers and GA4 Measurement Protocol

    One of the most challenging problems in web analytics today is measuring campaign traffic before a visitor accepts cookies. In an opt-in setup with tools like OneTrust or CookieYes, Google Tag Manager and GA4 often cannot record campaign events until consent is granted, which creates a blind spot exactly where marketers most want visibility. Why…

  • AI Has Grown Up. Now Stop Measuring It Wrong.

    AI Has Grown Up. Now Stop Measuring It Wrong.

    A follow-up to The Golden Hammer Syndrome — six months later, AI is delivering real ROI. The problem is we’re still asking the wrong questions. In January I wrote about using LLMs to check if a number is even. People laughed — and then sent me screenshots of their own codebases doing the same thing.…

  • 🦁 The Lion Roars Again: Real-Time Order Notifications from Allegro

    🦁 The Lion Roars Again: Real-Time Order Notifications from Allegro

    How I built a serverless order monitoring system with Cloudflare Workers that polls Allegro’s API every 3 minutes and triggers webhooks for new orders — all for $0/month. The Story So Far Remember a month ago when I built that order notification system and had a lion roar every time a new order came in?…

  • Async AI Image Generation with Cloudflare Workers & Make.com

    Async AI Image Generation with Cloudflare Workers & Make.com

    How I solved the 40-second timeout problem by splitting content automation into three decoupled stages — without rewriting a single Make.com scenario. May 2026  ·  10 min read Background A few months ago I wrote about automating WordPress article publishing and social media distribution with Make.com and LLMs . The pipeline was working great: read a recipe…

  • Fully Automated AI Video Production Pipeline

    Fully Automated AI Video Production Pipeline

    From a single prompt to a finished film — no manual editing required. Over the past few days I built something that fundamentally changed how I think about video content production. Instead of hours in an editor, an entire short documentary is generated from one text instruction. Here is how the system works and why…

  • Lion Roars Every Time Someone Buys My Book (WooCommerce → Twilio SMS Notification

    Lion Roars Every Time Someone Buys My Book (WooCommerce → Twilio SMS Notification

    A story about email push notifications lying to you, and why SMS saved the day. The Goal: A Lion Roar for Every Order I publish children’s audiobooks. One of the main characters in our book series is a lion — bold, brave, and impossible to ignore. The series is a family project: my daughter is…

  • Zero-Touch QA: Automating Playwright Test Generation with Copilot Skills and MCP

    Zero-Touch QA: Automating Playwright Test Generation with Copilot Skills and MCP

    Writing robust end-to-end tests for a live, multi-page application you do not own is notoriously difficult. Without access to local development environments, Storybook components, or internal feature flags, you are left manually inspecting the DOM to figure out how things work. However, the testing landscape is shifting rapidly. By leveraging GitHub Copilot’s extensible architecture, I…

  • Building a Gluten Label Scanner on Cloudflare Workers AI (Gemma 4)

    Building a Gluten Label Scanner on Cloudflare Workers AI (Gemma 4)

    I started this project because I wanted to test the newly introduced Gemma 4 model with Workers AI stack and compare it against my older production-style application built on Next.js + Vercel + Google API (Gemini 3): https://gd.marketscanai.com/en. I built a production-ready gluten label scanner using Cloudflare Workers + Workers AI, with the @cf/google/gemma-4-26b-a4b-it model…

  • The Era of AI Chat is Over. It’s Time to Issue Orders.

    The Era of AI Chat is Over. It’s Time to Issue Orders.

    The tech industry has a massive blind spot when it comes to Artificial Intelligence. If you read the standard advice online, everyone tells you that the secret to mastering Large Language Models (LLMs) is learning how to have a better “chat.” The prevailing wisdom treats the algorithm like a new hire on your team: brainstorm…

  • How I Optimized a Heavy Image Gallery to 99/100 in Lighthouse with AI

    How I Optimized a Heavy Image Gallery to 99/100 in Lighthouse with AI

    After a few years of neglecting it, I finally decided to spend a moment refreshing my personal website. I thought it would be a perfect opportunity to not only learn something new but also to test how AI tools—under proper supervision—can handle a very typical, yet notoriously tricky web development problem: heavy image optimization. My…

  • I Built a Browser Game in 2 Hours on a Free Weekend – No Coding

    I Built a Browser Game in 2 Hours on a Free Weekend – No Coding

    Last weekend I had some free time and a wild idea: what if I built a fully playable browser game from scratch — design, code, assets, and deployment — in a single afternoon? No team. No budget. Just a concept, a few AI tools, and roughly two hours. The result is Steki Kuby — an…

  • From Concept to AI Autoresponder in 60 Minutes

    From Concept to AI Autoresponder in 60 Minutes

    It all started with a casual question from a friend. Google had just released its new Google Workspace CLI, offering programmatic access to every product in the suite -including Gmail. The question was: “What if we wrote a program that checks new emails and replies to them using a style learned from your previous messages?”…

Follow Me On Instagram

@pluszinsta

This is how it all started…

When I was a child, I watched a movie “Capital City” with a scene where an IT specialist worked remotely on his laptop, tackling a technical issue. That scene sparked my desire to work in that way.

From Atari to PCs, dial-up (PPP), ASP, and beyond, there was a lot of learning and studying. I worked while I studied, explored new programming languages and areas of technology, eventually leading a team. Startups, remote work, and even AI – it’s been a journey!

Continuously learning, curiosity, and a balanced life are the keys to success in this field.

Engineering manager, team lead, architect, developer