AI
Harness (Systems) Engineering
After the shift from prompts to context engineering, what comes next? Using recent themes from the Anthropic engineering blog as clues, this article connects token efficiency with three emerging directions: harness design, evals, and containment.
How to Save AI Tokens
Measure AI coding token costs with a React POC and cut them using prompt caching, subagents, lean MCP, context engineering, and Cursor Composer.
How Tokens Work
How BPE creates tokens, embeddings feed LLMs, prefill and decode shape pricing, and KV cache and prompt caching reduce repeated-input costs.
AI Agent Tools
A practical map of the AI coding agent ecosystem: the differences between CLAUDE.md, AGENTS.md, and SKILL.md; how MCP, Serena, and CodeGraph work; the layers of code intelligence; and how to discover emerging tools through GitHub Trending.
The AI Frontend Engineer
In an era when AI writes code for us, how can frontend engineers grow and survive? Drawing on verified sources including Karpathy’s agentic engineering, Vercel v0, the Stack Overflow Survey, and METR research, this article outlines the new skills and learning strategies centered on verification, specification, and judgment.