AI Programming
34 posts
How Do 40+ Tools 'Grow' onto an AI?
Deep dive into Claude Code’s tool system: how 40+ tools form an extensible capability architecture through unified interface contracts, three-tier filtering pipelines, and fail-closed defaults. From Tool.ts interface to buildTool factory, revealing the underlying mechanisms of AI tool calling.
Tool Execution Orchestration——The Art of Parallelism, Streaming, and Interruption
Deep dive into Claude Code’s tool execution orchestration mechanism: the complete permission checking flow, concurrent execution scheduling strategy, streaming progress propagation, and the implementation principles of user interruption.
Claude Code Is Not a CLI Tool, But a 'Living' System
A deep dive into Claude Code’s underlying architecture: why it’s not a traditional CLI tool but an intelligent system running in a ‘distributed state.’ From TypeScript to Bun runtime, three-tier architecture to Feature Flags, understand the core design philosophy of this AI coding assistant.
Reverse Engineering Claude Code's API Request Signing
An in-depth reverse engineering analysis of Claude Code’s API request signing mechanism, revealing how the cch hash and xxHash64 are implemented, the secrets of Bun’s runtime, and how Anthropic protects API calls with native code.
Claude Code Memory System: The Complete Guide to Making Your AI Assistant Remember Your Project
Deep dive into Claude Code’s memory mechanisms: Auto Memory vs CLAUDE.md, hierarchical memory structure, modular rules configuration, making your AI assistant truly remember your project habits.
The Redis Author Had AI Write an Emulator, 30 Minutes to Run Through All Z80 Instructions
Redis founder antirez used Claude Code to implement a complete Z80 emulator in 30 minutes, passing the ZEXALL full instruction test. He designed a strict clean-room experiment: first had AI organize documentation, then cut off the network and implemented from scratch. Result: 1200 lines of code, zero bugs, and顺便 also built ZX Spectrum and CP/M environments.
RAG in Practice: Stop Making Your LLM Take Closed-Book Exams
A practical RAG tutorial: build an enterprise knowledge base Q&A system in 4 steps using embedding vector search and Claude. Contextual Retrieval cuts retrieval failure from 5.7% to 1.9%, with full Python code and Voyage AI model comparison.
Tool Use: Teach AI to Make Phone Calls and Get Help When It's Stuck
Claude can’t do math or query databases on its own. But you can teach it to ‘make phone calls’ — give it the numbers for calculators, databases, and other tools, and let it dial when needed.
Prompt Chaining: Make AI Check Its Own Work and Double Accuracy
Writing requires revision, and so do AI responses. Learn how to use prompt chaining to make Claude self-review and improve, dramatically boosting response accuracy. Like having AI write a draft, check it, polish it, and hand you a perfect final answer.
Prompt Engineering Lesson 2: Clear and Direct is King
Anthropic’s official tutorial chapter 2: Why does Claude keep missing the point? Because your prompts aren’t clear enough. Learn this one trick to make AI understand you precisely.
