In Chapter 1 I claimed our entire Auth Gateway is built on top of one NGINX directive: auth_request. This chapter is a deep dive into how that directive actually works, and the four or five sharp edges that bit us before we got the config right. If you already know auth_request cold, skim to "Sharp edge 1" near the bottom — that's where the real war stories are. auth_request actually does Drop t
Most text analysis solutions fall into one of two problems: Too expensive — OpenAI API costs money for every call Too complex — Hosting your own Hugging Face model requires infra, GPU, maintenance I built TextAI Pro — a lightweight REST API that does the job without the overhead. Two endpoints: POST /analyze Sentiment: positive / negative / neutral Confidence score (0–1) Top keywords Word count PO
J'ai un aveu à faire : pendant longtemps, quand un dev me montrait fièrement son app Python avec un bouton gris carré et une Listbox qui sentait Windows 95, je hochais la tête poliment. Aujourd'hui, j'ai arrêté. Pas parce que je suis devenu méchant. Parce que PyQt6 existe, et qu'il n'y a plus aucune excuse. Cet article, c'est ma tentative de te convaincre — toi qui ouvres encore tkinter par réflex
AI Can't Fix What It Can't See: How cdk diagnose Enables Autonomous CDK Remediation Current Behavior vs. What We Want Today, when a CDK deployment fails through a pipeline, the remediation loop looks like this: Developer ──▶ Push code ──▶ Pipeline ──▶ CFN deploy ──▶ ❌ Fails │ ┌───────────────────────────────────────────────
You ask Claude to "add caching to the user profile endpoint," and 30 seconds later you ship something that looks fine in review: SET user_42 <json> — flat key, no namespace, collides the moment a second service shares the cluster. No TTL — the entry lives forever until maxmemory evicts your hottest keys. KEYS user_* in a cleanup job — single-threaded Redis stalls every other client for hundreds of
Let's start with a controversial opinion: API documentation, as we know it, has failed. Think about it. Docs are: Static: They can't adapt to your specific question or use case. It's time for a new paradigm: Interactive API Intelligence. Instead of pulling information from a dead document, what if we could query the knowledge in a conversational way? This isn't just a theory. I've spent the last f
LLMs hallucinate. That's not news. What's underdiscussed is how that failure mode behaves in long working sessions: confident reconstruction that looks fluent, cites specifics, and feels right — until three sessions later when something supposed to be true turns out not to be. This is week 5 of an 8-week deep dive on CRAFT for Cowork, a structured working environment for Claude. The QA framework t
You don’t notice the problem right away. Everything runs smoothly in MySQL… until a new report shows up. Then queries slow down, dashboards lag, and you start realizing you’re stretching the database beyond what it’s good at. That’s usually when BigQuery enters the picture. So the real question becomes: How do you actually move data between them without turning it into a side project? Let’s w