Category: AI & Machine Learning
-
Too Many School Messages? I Built a Local AI Triage for Librus in One Hour
A macOS agent that polls my kids’ school inbox every hour, classifies each message with a Polish decision model running on my own GPU, and only disturbs me when something actually needs a parent. The problem: notification fatigue, Polish-edition Librus Synergia is the dominant electronic gradebook in Polish schools — grades, attendance, homework, and an…
-
AI migrated my EC2 and 11-year-old Redmine to the newest version while I took a shower
My Redmine was old. Not “a bit behind” old — Redmine 3.3.2, installed in 2017, running on Amazon Linux AMI 2018.03, an operating system that reached End of Life at the end of 2023. The EC2 instance itself was launched in 2015. Every SSH login greeted me with a nice ASCII-art banner warning that the…
-
How I Protected Downloadable Audiobook MP3s with AI Watermarking
The Problem: Not Everyone Streams My daughter and I create a Polish children’s audiobook series — Zwierzęta Detektywi (Animal Detectives). We publish episodes on Spotify and Apple Podcasts, and that works great for most families. Then one of our customers asked: “Can I get the MP3 files? My kid uses an old MP3 player —…
-
Understand Any AWS Environment with AI and the AWS CLI
You inherited an AWS account and nobody can tell you how the pieces fit together. Here is a fast, read-only workflow that pairs the AWS CLI with an AI assistant to map compute, networking and routing —* and turn the raw JSON into clean architecture diagrams. 1. Why CLI + AI beats clicking around the console The…
-
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.…
-
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
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…
-
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 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
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…
-
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?”…
-
Building a Real LEGO Sales App with AI: Why Project Decomposition Matters More Than Prompt Magic
AI tools can generate code quickly, but shipping a working app still depends on one old-school engineering skill: breaking the project into clear parts, defining system boundaries, and configuring each layer correctly. The Principle I Keep Relearning When people talk about building with AI assistants like Codex, the conversation often focuses on prompts. In practice,…
-
Vibe‑Coding a Real App with AI in 3 Hours: What the Free Tools Don’t Tell You
It started with a tweet. A Polish traffic‑safety journalist (https://x.com/_zboral) wrote that if someone in IT really wanted to, they could topple the local driving‑school industry in a week by launching a free website with driving‑test questions. The data is public, he said, and linked to the government portal hosting the official question set. Someone…
-
The Golden Hammer Syndrome: Why We Need Less AI and More Engineering
Stop burning GPU cycles to check if a number is even. A guide to regaining our technical sanity. It is an old adage in the toolbox of life: “When all you have is a hammer, everything looks like a nail.” In 2026, that hammer is the Large Language Model (LLM), and we are currently smashing…
-
Don’t Teach AI – First Teach People to Ask Questions and Verify Answers
The conversation around AI enablement often focuses on training models, fine-tuning prompts, improving usage metrics and optimizing workflows. But here’s an uncomfortable truth: if your organization struggles with innovation today, AI won’t magically fix that tomorrow. The real barrier to AI adoption isn’t technical—it’s cultural. And it starts with something surprisingly basic: the ability to…