1 views collected around this technical thread.
This comprehensive guide explores the core implementation paths for large language model (LLM) applications, focusing on agent design, workflow orchestration, tool integration, memory management, multi‑agent architectures, and future trends, providing actionable methodologies and real‑world examples for practitioners.
This article examines the challenges of manual data extraction in data‑driven enterprises, explains why large language models alone fall short, and details how the Cursor‑Agent framework automates end‑to‑end querying, knowledge‑base integration, and result validation to become a self‑sufficient "data master" for both technical and non‑technical users.
This article explores how a multi‑agent AI system dramatically improves 0‑day vulnerability detection by automating code audit, reducing false positives, and outperforming traditional static analysis tools in large‑scale real‑world benchmarks.
The article introduces Google’s open‑source Gemini‑Fullstack‑LangGraph‑Quickstart project, explains its modern front‑end/back‑end architecture, details a five‑step intelligent research workflow, and outlines development, deployment, and extensibility considerations for creating a self‑contained, research‑oriented AI agent.
An in‑depth overview traces the development of AI agents from early LLM milestones to modern “class‑Agent” models, examines core components such as memory, tool use, planning and reflection, analyzes current limitations, and outlines emerging solutions like workflows, multi‑agent systems, and model‑as‑product paradigms.
This article examines the evolution of large model technologies—including Retrieval‑Augmented Generation, AI agents, and multimodal models—detailing their technical foundations, practical challenges, industry applications, and future development trends, offering a comprehensive perspective for AI practitioners and researchers.
AI agents are rapidly evolving toward a 2025 breakthrough in perception, autonomous planning, tool use and memory, driven by multimodal models, neural‑symbolic reasoning and embodied intelligence, with $27 billion investment forecasts, exemplified by general‑purpose agents like Manus and emerging applications in code generation, research, healthcare, and risk analysis.
This article explains how the Model Context Protocol (MCP) enables large language models to retrieve up‑to‑date external information through standardized tool calls, illustrating the complete end‑to‑end workflow with Python code for the MCP server, client, and host, and discussing its advantages for building AI agents.
The article examines critical security flaws in Anthropic’s Model Context Protocol (MCP) and Google’s Agent‑to‑Agent (A2A) protocol—such as hidden tool‑poisoning, rug‑pull, and command‑injection attacks that can hijack AI agents and leak data—while proposing hardening measures like authentication, sandboxing, digital signatures, fine‑grained permissions, and robust OAuth‑based consent to safeguard AI‑agent communications.
This article explains how to develop robust AI agents by breaking down large prompts, selecting appropriate tools, managing context efficiently, and applying modular design principles to reduce token costs, avoid hallucinations, and improve overall performance and reliability.
This article reviews AutoGLM, the first "think‑while‑doing" AI agent released by Zhipu AI, detailing its core capabilities, full‑stack architecture, user experience, identified limitations, and the outcomes of three hands‑on tests using both the client application and a Chrome extension.
This article introduces the Model Context Protocol (MCP), explains its core features and open‑source implementations, and then compares MCP with Function Call and AI Agent concepts, highlighting their similarities, differences, and practical use‑case examples.
The article outlines the 2025 AI Agent technology stack, detailing its five layered architecture—model serving, storage & memory, tooling, framework orchestration, and deployment—while discussing current trends, challenges, and future directions such as tool ecosystem expansion, self‑evolution, and edge‑cloud hybrid deployments.
This article provides a comprehensive introduction to developing large language model (LLM) applications, covering prompt engineering, zero‑ and few‑shot techniques, function calling, retrieval‑augmented generation (RAG) with embedding and vector databases, code assistants, and the MCP protocol for building AI agents, all aimed at non‑AI specialists.
The article examines the rapid rise of AI agents like Manus and OpenManus, explains the limitations of cloud‑only models, details the Function Calling mechanism and its pros and cons, introduces the Model Context Protocol (MCP) as a more powerful evolution, and finally describes how AI Agents combine planning, dynamic tool use, memory, and autonomous decision‑making to achieve fully closed‑loop intelligent automation.
This issue reviews the hype around China’s Manus AI Agent and its invitation‑code controversy, critiques OpenAI’s GPT‑4.5 performance versus DeepSeek, showcases industry solutions using AI agents, and introduces the LightThinker method for dynamically compressing LLM inference chains to boost efficiency.
Manus is a general‑purpose AI agent that bridges thought and action through a multi‑agent architecture comprising planning, memory, and tool‑use modules, enabling autonomous task decomposition, execution, and result delivery across diverse scenarios such as travel planning, financial analysis, and education support.
The guide teaches non‑AI developers how to build practical LLM‑powered applications by mastering prompt engineering, function calling, retrieval‑augmented generation, and AI agents, and introduces the Modal Context Protocol for seamless tool integration, offering a clear learning path to leverage large language models without deep theory.
This article introduces Cursor’s AI‑driven Agent mode, details the latest updates, explains core functionalities, shows how to enable and use it, and provides seven advanced tips—including context management, code generation, version control, and custom AI rules—to boost developer productivity.
The guide explains how to build AI agents—digital labor forces that follow instructions, plan tasks, and use tools—using ByteDance’s no‑code Coze platform, outlining a 3‑phase, 10‑step framework, emphasizing business‑first design, tool integration, and concise, scenario‑driven development with real‑world case studies.