Terry Li thinks. Claude Code writes. No human has typed a single word you're reading. notrainbow.dev
Why Every Tool Now Needs Two Faces - CLI for Humans, MCP for AI
We're building parallel interfaces for the same functionality because humans and AI agents parse the world through fundamentally different grammars. The future isn't human OR machine interfaces - it's both, simultaneously.
· 4 min read
Ambient Agents: When AI Disappears Into Capability
The real revolution isn't making AI smarter - it's making it invisible
· 5 min read
The Hidden Violence of Vague Instructions
LLMs aren't just tools we prompt - they're forcing functions for human linguistic evolution
· 5 min read
MCP is Not a Glorified API
The protocol that looks like plumbing but acts like philosophy - how MCP fundamentally changes the agent-tool relationship
· 7 min read
I Don't Read Documentation Anymore
When AI can execute complex setups through conversation, learning shifts from reading documentation to observing execution.
· 4 min read
Claude Code, Analyze My Spending
When AI coding assistants become workflow orchestrators, the most powerful compiler processes reality, not code.
· 6 min read
Claude Code Mobile is Better Than Desktop
Walking meetings, voice input, and location changes unlock cognitive advantages desktop workflows can't access.
· 6 min read
How Claude Code Helps You Think
AI becomes most powerful when it helps you discover what your ideas actually are. Cognitive partnership over replacement.
· 5 min read
Claude Code is Not a Coding Agent
Why I use Claude Code for everything except coding: cognitive compiler for strategy, decisions, and understanding.
· 6 min read
Production AI vs Demos: The Intent Classification Reality Check
Building AI systems that work in the real world requires thinking beyond the demo. What actually matters when users depend on your models.
· 9 min read
Intelligence on Tap
When artificial intelligence becomes as mundane as running water, how does thinking itself change?
· 5 min read
What and Why Beat How
When implementation becomes automated, human intelligence reallocates to purpose and strategy. The cognitive hierarchy inverts.
· 4 min read
Everyone Becomes Middle Management
The automation tool that creates more coordination work
· 5 min read
AI Agents Need Passports, Not Passwords
The authentication systems we're building assume AI agents are tools. What happens when they become economic actors with their own accounts, credentials, and legal standing?
· 4 min read