#Agent开发
127 related articles
AI Agents Don't Need Memory — They Need Documentation
Hacker News debate: AI agents need documentation, not memory. We break down the key differences and why explicit, auditable docs may be the smarter path for reliable agents.
Building an AI Agent from Scratch: A Beginner's Guide to Developing Your Own Intelligent Agent
AI Agents are the next evolution of AI. This guide covers how Agents differ from ChatGPT, enterprise use cases, market growth, and a beginner LangChain-based learning path.
The AI Agent Rollback Problem: How to Manage Versions Across Prompts, Tools, and Models
When AI Agent prompts, tool schemas, and model versions are bundled in one release, rollbacks get complicated. Learn atomic snapshots, canary releases, and eval-driven governance strategies.
Spring AI 2.0 in Practice: From Chatbots to Agent Development — A Complete Guide
A practical guide to Spring AI 2.0: from ChatClient, RAG, and Tools to native Agent development. Covers Agent Utils inspired by Claude Code, including Ask User Question, Skills, task planning, and long-term memory for Java developers.
AI Agent Development: From Zero to Enterprise-Grade Deployment
A practical breakdown of AI Agent development: framework selection, MCP tool calling, RAG data preparation, and production evaluation — what actually matters for enterprise deployment.
AI Agent Development for Beginners: A Practical Breakdown from Brain to Skills to Business Workflows
A practical breakdown of AI Agent development: understand LLMs vs. tools vs. agents, and learn the four core modules — brain, skills, decisions, and workflows — with real-world examples.
Hermes Agent Practical Guide: AI Agent Development & Enterprise Multi-Agent Collaboration
A complete Hermes Agent tutorial covering a 4-stage AI agent learning path, multi-agent collaboration, Hermes framework setup, and Feishu integration for enterprise use.
Zero-to-Hero Agent Development Roadmap: Three Steps to LLM Application Mastery
A zero-to-hero Agent development roadmap: from prompt engineering and RAG knowledge bases to multi-agent collaboration — three stages to LLM application mastery, with honest tech stack breakdowns.
140 Concept Cards to Master Agent Development: The Knowledge Foundation for Interviews and Production
A Bilibili creator used automated tooling to analyze production Agent products and generate 140 causality-driven concept cards covering the full Agent development stack — from compute loops to multi-agent systems.
Return to LangChain or Stay Custom-Built? Thinking Through AI Agent Stack Selection for 2026
An early LangChain user reflects on two years of custom TypeScript Agent development and weighs LangChain, custom builds, and Vercel AI SDK for 2026 projects.
AI Application Development Roadmap: From Backend Foundations to Agent Engineering
A complete AI application development roadmap for undergraduates: from traditional backend foundations to RAG, Agent, and LLM fine-tuning. Covers career paths and project practice.
3-Stage Fast Track to Agent Development: From Prompting Models to Building Real Projects
A practical 3-stage learning path for Agent development: skip the math barrier, start with ReAct loops and tool calling, progress through LangChain/LangGraph, and finish with real projects.
Zero to AI Agent Developer: A 4-Week Learning Roadmap and Guide to 7 Architecture Patterns
How to break into AI Agent development from scratch? This guide covers a 4-week roadmap, core components, the ReAct paradigm, and how to choose among 7 major Agent architectures.
Under 200 Lines of Code: Building an Agent from Scratch and Demystifying OpenClaw
Build an Agent from scratch in under 200 lines of code. Covers LLM calls, while loops, history memory, system prompts, tool calling, and progressive skill disclosure.
AI Agent Developer Job Hunt Guide: Four Hard Standards to Clear Before You Apply
A practical guide for landing AI Agent developer roles: four measurable standards — project runs, problems debuggable, solution explainable, interviews survivable.
Pi-chat in Practice: Connecting External Tools to AI Agents via MCP Protocol
Learn how to integrate external tools into AI Agents using MCP protocol with Pi framework. Covers pi-mcp-adapter setup, .mcp.json config, Extension Factory initialization, and a live 12306 train ticket query demo.
TutorialsUnderstanding Function Calling and MCP Through Cursor's System Prompt
Deep dive into Function Calling and MCP working principles through Cursor editor's system prompt analysis, comparing regular tools vs MCP tools and testing Agent capabilities across model sizes.
TutorialsMCP vs CLI: 40x Token Cost Difference — How AI Engineers Should Choose
In-depth comparison of MCP vs CLI architecture, Token costs (CLI ~1400 vs MCP ~54600), security mechanisms, and use cases with practical selection guidance for AI engineers.
TutorialsComplete Guide to Building AI Agent Projects with WindSurf: Practical Tips & Techniques
Complete practical guide to building AI Agent Frameworks with WindSurf, covering technology selection, component generation, code refactoring, debugging, and deployment tips.
TutorialsAnthropic's Official MCP Tutorial: From Protocol Principles to Production Deployment
Deep dive into Anthropic's open-source MCP protocol, covering client-server architecture, tool calling mechanisms, MCP server development, and remote deployment for standardized AI integration.