Occasional sharing
This article analyzes AI Agent context engineering, explaining how context, memory, RAG, and harness interact, how information is organized, compressed, and debugged, with practical examples from AgentScope source code.
The author details a Spec-Driven Development (SDD) practice that structures a .specs repository with state-gated phases, four-file feature specs, evidence grading, and reusable skills to let AI agents independently investigate, design, implement, and verify features while reserving business decisions and external side effects for human approval.
This article provides a comprehensive analysis of AI Agent Skills, detailing their historical roots, differences from tools and prompts, directory structure, metadata specifications, execution flow, classification of skill types, multi‑tenant isolation, security considerations, and practical engineering guidelines for building and deploying reusable agent capabilities.
This article explains why AI agents need function calling, describes the structured tool‑call protocol between LLMs and runtimes, shows how to define and secure function tools, and provides best‑practice code and checklists for production deployments.
A four‑day sprint turned into a week‑long integration effort, revealing hidden code paths, mismatched documentation, signature confusion, and field‑mapping errors, which were finally untangled by an AI Agent that mapped entry points, generated replayable curl commands, and produced a structured hand‑off document.
The article breaks down how AI agents extend large language models by adding tools, memory, and looping mechanisms, explains the ReAct paradigm and its evolution, compares agents to traditional workflows, and outlines product perspectives, coding advantages, current maturity stages, and typical use‑case categories.
Analyzing 813 AI‑related positions from 555 Beijing companies, the author uncovers a startup‑dominated market, a shift from model competition to Agent‑driven automation, and emerging talent demands such as Multi‑Agent, RAG, and deployment expertise.
This roundup highlights five noteworthy projects—Claude Code engineering skills, a Rust‑based terminal programming Agent, a persistent memory layer for AI coding Agents, the GPU‑accelerated Zed 1.0 editor, and pay.sh’s native Agent payment gateway—each illustrating a different layer of Agent engineering and its emerging ecosystem.
This article reviews five standout GitHub‑trending AI Agent and developer‑tool projects—ruflo, AstrBot, context‑mode, AionUi, and TradingAgents—detailing the problems each solves, why they attracted rapid star growth, and which engineers would benefit from adopting them.
The article dissects Claude Code’s memory system, showing that the real challenge is deciding what information to keep and when to discard, and it details design principles, index‑content separation, LLM‑based retrieval, expiration handling, write‑path isolation, and practical improvements applied to the author’s own agent platform.
