Posts
All the articles I've posted.
REST vs GraphQL vs gRPC: When to Use Each API Style
Posted on:July 15, 2026REST vs GraphQL vs gRPC is one of the most common API design decisions in system design interviews and real architectures. Here is how each one works under the hood, where they break in production, and when to use each.
How to Know Your RAG Changes Actually Helped
Posted on:July 13, 2026Measuring RAG Retrieval Quality with Precision, Recall, and LLM-as-Judge.
Building a Claude Code Plugin for Your API Stack
Posted on:July 6, 2026A practical walkthrough on packaging your team's conventions into a Claude Code plugin, using a Node.js, TypeScript, NestJS, Docker, Vitest, Supertest, and GitHub Actions API as the example.
Claude Code in Production: Velocity Gains From Real Engineering Team
Posted on:July 3, 2026How my engineering team put Claude Code, custom skills, and RAG applications into daily production work, without lowering our quality bar.
Multi-Agent Systems: When One AI Is Not Enough
Posted on:June 29, 2026Single agents hit a ceiling fast. Here's what multi-agent architecture looks like in practice, the patterns that actually hold up, and the coordination problems no one warns you about.
Rate Limiting: The System Design Concept You Can't Afford to Skip
Posted on:June 25, 2026Fixed window, sliding window, token bucket. How rate limiting works, why distributed rate limiting is the part most people get wrong, and how to build it correctly with Redis and Lua atomic scripts.