Wiring a local network scanner into an AI assistant with MCP
I build DeviceShelf, a local-first network scanner. Its Server edition is the headless, always-on...
Tutorials
Breaking the Physical Wall: The Ultimate Guide to Heterogeneous AI Parallelism on Android
In the early days of mobile machine learning, the developer's journey was simple, if a bit primitive....
I had Qwen build a Qwen-powered app — and sat in the reviewer's chair
Most hackathon posts are about what the AI does. This one is also about who wrote it. QuotePilot — an...
I'm Not Coding Anymore, and That Is Ok
I am a hands-on software engineer with more than 17 years of experience, and I no longer write code....
Yes, another tree classifier. Here's what building one from scratch taught me.
I spent way too long building a tabular classifier from scratch. It doesn't beat XGBoost. I'm...
Quality is the new Quantity
AI made writing software cheap. That is the obvious story. More code, more prototypes, more pull...
Lesson 2 - Security: Secure as you build
Two supply-chain compromises landed in my dependency tree in one week, days before I meant to call the build done. I froze. Here is what I did next, and why AI-era security can't w...
We taught AI agents to check who they're talking to (build notes)
My coding agent will connect to anything. Yours will too. Point Claude Code, Cursor or Codex at an...
How to Use Claude Code Plugins (Install from a Marketplace or Build Your Own)
Claude Code plugins bundle slash commands, skills, agents, hooks, and MCP servers into one installable unit. The /plugin marketplace flow, plugin.json anatomy, and when a plugin be...
Votre Agent IA est crédule : Pourquoi le "Prompt Engineering" ne vous protègera pas en production
La semaine dernière, nous avons vu comment réduire vos coûts d'API en routant les tâches simples vers...
I Built a Self-Hosted AI Incident Diagnosis Tool That Only Returns a Root Cause When Multiple Diagnoses Agree
Most AI incident diagnosis tools will happily produce a root cause even when the evidence is weak....
AWS Lambda MicroVMs alternative: agent sandboxes in the EU
On 23 June 2026, AWS shipped Lambda MicroVMs: isolated VMs you launch, suspend, resume and terminate...
The pool that got slower the more we shared it
How a live LLM+MCP diagnostic session found a hidden ArrayPool.Shared cross-thread contention point that no static analyzer would ever flag — and why the fix had nothing to do with...
Most code review catches bugs. I shipped one that argues with the design.
The cheapest bug to catch is the one a reviewer circles on line 40. The expensive one never shows up...
8 Things Developers Confidently Explain After Watching One YouTube Video
I just got back from my vacation which, like 99% of Polish people, I spent in Croatia. Dobar dan!...
Building a Hybrid Docker Orchestrator in Go: The Journey from Single VM to Multi-Node Cluster
What if you could combine the native simplicity of Docker Compose with the decentralized targeting...
Claude Code subagents: when to delegate, and when a rule or hook is enough
Your main conversation's context window is the scarcest resource you have. Every search result, every...
One Markdown File, 15 Landing Pages: Separate Your Copy From Your Design
An AI agent turned our brand references into 15 complete landing page designs, all reading identical copy. We clicked through them live and shipped the winner. Stack + AWS deploy i...
Comparing Two Eval Runs by Their Average Pass Rate Is the Wrong Test
TL;DR. You run version A and version B against the same 500-item eval set. A passes 71.4 percent, B...
Navigating Intellectual Property in Kenya
Kenyan Devs, Stop Assuming Your Code is Protected: A No-Jargon Guide to IP Law As software...
Open-source Grammarly alternatives in 2026 — and why I built another one
If you search "Grammarly alternative," you get listicles full of freemium tools that are just smaller...
How I made a Rust hot path 27x faster, and the AI fix I refused to merge
Two years ago I open-sourced KeyEcho, a small desktop app that plays a mechanical-keyboard sound the...
Designing for Non-Human Callers
Skills built for humans degrade silently at agent scale. Here's how stress-testing a Gherkin skill revealed four specific failure modes — and how to fix them.
The 3-Tier Skill Architecture in Practice
A 3-tier model for organising AI agent skills — org-wide standards, domain methodology, and personal workflow. Which tier owns the risk when patterns fail to transfer?