865,000 Tokens: Building NomFeed with Opus 4.6
From 6 billion tokens a month to 865,000 for a complete CLI tool. How architectural discipline around token economics produced 20x efficiency gains.
Archive
Essays on AI systems that need more than a good demo.
7 posts on agent architecture, production workflows, context engineering, tooling, and what breaks when the hype layer wears off.
Where Arabic Morphology Meets AI Engineering: Building a Morphologically-Aware Quran Search System
QRAG combines structural Arabic indices with multi-model AI pipelines to transform keyword search into deep linguistic analysis.
The Three-Layer Pattern for AI in Production Operations
Why I separated the reasoning engine from the chat interface — and what years of incident response taught me about building AI-augmented workflows.
The Walled Garden Era: What Anthropic's Claude Code Crackdown Means for AI Development
Anthropic blocked 650,000 developers at 2 AM without warning. Here's the economics, the enforcement pattern, and what it means for your AI stack.
18 AI Engineering Predictions for 2026 (With Confidence Levels)
18 specific AI engineering predictions for 2026, each with confidence levels and falsifiable criteria. Public scorecard dropping January 2027.
The AI Coding Force Multiplier: Three Patterns That Compound
Workflow prompts deliver consistency. Single-file scripts deliver power. Directory watchers deliver scale. Together, they multiply: 1 + 1 + 1 = 10, not 3.
Context Engineering: The Complete Guide for Senior Engineers
Progressive disclosure, file-based persistence, sub-agent delegation, and Skills vs MCP - reduce tokens by 94%, cut costs 36x.