I Built a Backend Platform with Flat Pricing While Working Night Shifts in an ER
The Problem Every backend-as-a-service platform bills you on usage. More rows, more...
Tutorials
Everyone Wants AI Agents: So Why Are They So Damn Hard to Build?
Over the past year, AI agents have gone from research experiments to one of the hottest topics in...
Two Terminals, One Screen: Building an Agent Cockpit That Tells the Truth About Cost
How I unified the Claude Code and Codex CLIs behind one local cockpit, and why the spend view refuses to fabricate a dollar figure it cannot measure.
Why Your AI Code Reviewer Keeps Missing Bugs (And What Actually Works)
You've probably noticed it by now. You throw a hairy piece of code at Claude or ChatGPT for review,...
Structured Output From Local LLMs: JSON That Never Breaks (Ollama + Zod)
A 1.5B model running on your laptop will return JSON that almost parses. The closing brace is...
I Let AI Write My Backend Code for a Week — Here's What Actually Broke
I told myself it would be fine. I had been using AI coding assistants for suggestions and...
I Was Spending €50/Month on AI APIs — Now It's €5. Here's the Real Math.
I Was Spending €50/Month on AI APIs — Now It's €5. Here's the Real Math. Spoiler: the most...
I built Reclaim: an AI tool that finds medical billing errors and writes your appeal letters
Americans owe $220 billion in medical debt, and 80% of medical bills contain errors — duplicate...
How I stopped fighting AI API chaos with a simple proxy
I recently took on a side project that needed to tap into multiple AI models – GPT-4 for complex...
Claude just passed ChatGPT in US business spend — and Claude Code agents start billing separately
Claude just passed ChatGPT in US business spend — and Claude Code agents start billing...
Running Claude Code as an operations system: field notes
Most people meet Claude Code as a coding assistant: open a repo, ask it to fix a bug, review the...
Cutting AI Text-to-Speech API Costs: My 2026 Analysis
Honestly, cutting AI Text-to-Speech API Costs: My 2026 Analysis I spent the last six months...
Is your Magento store legible to AI assistants?
Ask ChatGPT or Claude for "a waterproof hiking watch with a barometer under 200" and you don't get...
Tokens: Why ChatGPT Can't Count the R's in 'Strawberry'
A language model never sees letters or words — it sees tokens, chunks of ~4 characters. Understand tokens and a lot of AI's quirks (and your bill) suddenly make sense.
I Built 'Chat With Your Docs' From Scratch — Supabase + pgvector + a Free Local Embedder
Production RAG, explained from zero: retrieve the right chunks with Supabase pgvector, then let an LLM answer using only those. The grounding trick that kills hallucinations. Day 4...
Going Remote, Without Going Reckless: Multi-LLM Orchestration and the New Front Door in llm-cli-gateway 2.9.0
The earlier posts in this series were about what the gateway lets you call (cache-aware spawning...
Thirty-Two Projects, One AI Pair Programmer
What I learned building 32 projects with Claude — games, Blender scenes, local AI stacks, a search engine — and the method that made it all work.
From Billing Alerts to Autonomous Action: Building SpendPilot with Qwen Cloud.
Introduction Cloud waste is a silent budget killer. Industry reports estimate that companies waste up...
Hardening API Scan Boundaries in skill-scanner, with sqry as the Review Map
On 14 June 2026 I cloned cisco-ai-defense/skill-scanner, set up the locked uv environment, and worked...
Building a Production-Grade MCP Memory Server: Lessons from MindCore
AI agents forget everything between sessions. Here's how we built an MCP memory server that actually...
Deploying Gemma 4 26B on Proxmox: IaC Setup with Terraform, Ansible & AMD iGPU
A complete guide to automating a local AI stack on Proxmox LXC using Terraform and Ansible, including Open-WebUI and AMD Radeon Vega iGPU workarounds.
Your AI agent is running an agentic loop right now. Do you know where it can fail? - 04 of 21
In 2026, understanding the agentic loop is as fundamental as understanding HTTP was in 2005. Here's...
BNPL Income Verification in the UAE: CBUAE Rules and Automation
What UAE BNPL providers need to verify under CBUAE short-term credit rules, which income sources matter, and how automated income verification fits compliance.
Zero-Trust RAG: Defeating the Shared Private Link Deadlock in Azure Terraform
How to programmatically approve Azure AI Search Shared Private Links using AzAPI, and why your AI architecture will fail an audit without proper Identity Chaining.