~/blog
Blog
Articles and thoughts on web development, architecture, and technology.
Your agent's suffering is your technical debt speaking
A joke plugin makes AI agents groan at bad code. The real punchline is what it reveals about the code we write, and the code we let AI write for us.
read →Stop letting your agents write Markdown
Everyone is excited about AI agents generating HTML instead of Markdown. The output looks beautiful. But nobody is asking what it costs, or what we lose when every agent response becomes a single-use webpage.
The arms race for your trust: Mythos, Cyber and the security hype
Anthropic and OpenAI are fighting for market share with AI security tools they call "too dangerous" to release. But the facts tell a different story than the press releases.
The CLAUDE.md File: Give Your AI Permanent Memory
Every Claude Code session starts from zero unless you tell it otherwise. The CLAUDE.md file is how you give it persistent context about your project, your stack, and your preferences.
The Day Claude Deleted My Production Database
AI coding assistants are incredibly powerful until they decide to "fix" a corruption by wiping your database. A cautionary tale about backups and why dev boxes need them too.
Claude Code Hooks: Deterministic Control Over AI Workflows
While claude.md instructions are treated as suggestions, Hooks provide deterministic guarantees. Learn how to use pre- and post-tool hooks to enforce formatting, block dangerous commands, and standardize your team's workflow.
Putting AI to Work in Your Laravel Backend
Laravel now has real tools for AI integration. Here's how to move beyond naive API calls and build structured, testable AI features with Prism and the official Laravel AI SDK.
The AI is Not Your Friend: How I Secured Gemini on This Site
Most 'AI integrations' are just a chat box and a prayer. Here is how I built a secure, contextual, and bilingual assistant using Gemini 3.1 Flash Lite.
Superpowers: Teaching Claude Code to Think Before It Types
Out of the box, Claude Code starts writing immediately. Superpowers forces it to plan, test, and verify first. On structured workflows, TDD enforcement, and why discipline beats speed.
From Blind Generation to an AI Team: How to Take Back Control with Agents
Stop treating AI as a single author. Give it roles, let them argue, and you'll ship better software before you've written a single line of code.
// overview
- Articles
- 21
- Read time
- 83m
- Words
- 14,478