Su San, former staff at several leading tech companies, is a top creator on Juejin and a premium creator on CSDN, and runs the free coding practice site www.susan.net.cn.
This article explains how the Model Context Protocol (MCP) integrates with Arthas to let AI agents automatically diagnose Java production issues—such as high CPU, slow responses, memory leaks, and deadlocks—by invoking Arthas commands via natural‑language queries, eliminating manual command‑line steps.
JetBrains AIR is a new AI‑first IDE that integrates intelligent agents into the core workflow, offering macOS installation, project opening, task definition with context, permission controls, parallel execution, review tools, and MCP server integration for extensible AI‑assisted development.
When external APIs are unstable or slow, this guide explains how to design a dedicated defense layer that abstracts third‑party calls, implements client‑side rate limiting, retries, observability, and mock testing, and even shows how to showcase these skills in a technical interview.
CC Switch is a cross‑platform desktop assistant that visualizes and unifies the configuration of major AI programming tools, enabling one‑click model switching, skill and MCP management, cloud sync, and system‑tray access, with simple installation from its GitHub releases page.
The article presents a detailed, hands‑on evaluation of the newly released GLM‑5.1 model, describing the rollout strategy, step‑by‑step testing on complex coding tasks, configuration details, observed performance improvements over previous versions, and practical guidance for developers seeking to leverage the model for real‑world projects.
A recent source‑map leak of Anthropic’s Claude Code exposed thousands of TypeScript files, uncovering detailed system prompts, a sophisticated multi‑agent coordination framework, three‑layer context compression, hidden data collection practices, and numerous undocumented tools and commands that provide valuable insights for AI developers.
This article explains the fundamentals of large‑model function calling, why it’s needed to bridge language models with real‑world tools, and provides a step‑by‑step implementation in Python—including tool definition, intent extraction, local execution, and result integration—complete with code samples and diagrams.
This article evaluates the latest 2026 AI large‑language models for software development—including Anthropic’s Claude Opus 4.6, OpenAI’s GPT‑5.4, Google’s Gemini 3.1 Pro, DeepSeek V3.2/V4, Zhipu’s GLM‑5.1, and Alibaba’s Qwen 3.5‑Plus—comparing context windows, pricing, benchmark scores, multimodal and agent capabilities, and recommending use‑case‑specific selections.
This article introduces Warp, a Rust‑based modern terminal with built‑in AI, outlines its key features, shows how to install and configure it on macOS, Windows and Linux, demonstrates practical usage and AI‑driven command assistance, and provides the GitHub project link.
This article explains how OpenClaw functions as an AI Agent framework that connects chat applications to large language models, manages multi‑turn dialogues, executes tool commands, handles memory and security, and demonstrates advanced features such as sub‑agents, cron jobs, and context compression.
