How Agents Defend Against Prompt Injection: Security Engineering from Text Isolation to Tool Permissions
Why prompt injection is dangerous for agents, and how to build defenses with untrusted content isolation, least privilege, read...
Agent Harness Engine: Turning LLM Agents from Prompt Toys into Engineering Systems
An engineering view of Agent Harness Engine and why agents are runtime systems built from context, tools, permissions, sandboxe...
Getting Started with CC Switch: Installation on Windows, macOS, and Linux
A first-time developer guide covering download, installation, first launch checks, and safety notes.
Getting Started with Skills.sh: Downloading and Installing Skills for Codex
A first-time guide to installing Node.js, searching skills, downloading them into a Codex project, and validating installation.
Getting Started with Codex: Installation on Windows, macOS, Linux, and WSL2
A system-by-system guide for first-time Codex users covering install entry points, commands, verification, and common issues.
RAG Document Parsing Pipeline: How Parsing Quality Shapes Retrieval Quality
Notes on document parsing, structure preservation, chunk validation, and open-source reproduction before RAG ingestion.
Blog Refactor Roadmap: From Using AI to Reliable Systems
How this blog will grow around AI onboarding, core capabilities, AI engineering, and backend systems without becoming scattered...
Common Mistakes for the Level 4 AI Trainer Exam
Introductory exam notes for China's AI trainer certification.