#Agent
134 related articles
How Do Cursor, Claude, and ChatGPT Actually Work? A Full Breakdown of the AI Tech Stack
Starting from real-world use of Cursor, Claude, and ChatGPT, this article breaks down the AI tech stack layer by layer: agent loops and the MCP protocol, pretraining and reinforcement learning, tokens and quantization, RAG retrieval and model routing, streaming output, and GPU infrastructure—helping you understand what each layer of an AI product does.
Google Retakes Global #1 in Two Weeks: Gemini 4 Carbon Review
Google launches Gemini 4 Carbon just two weeks after its predecessor, reclaiming the top spot on the global intelligence index. We review its three-stage cybersecurity capabilities, long-horizon task performance, pricing traps, and tiered security rollout, with action advice for security teams, developers, and ordinary users.
Agentic RAG in Practice: From Principles to Code, Building an Intelligent Retrieval System Step by Step
Traditional RAG hard-codes retrieval timing, content, and count, causing irrelevant answers. This article, based on a Bilibili tutorial, breaks down Agentic RAG principles: wrapping retrieval as tools for LLM autonomous decision-making, with four-tool design and complete code implementation to build a self-correcting, multi-hop intelligent retrieval system step by step.
RAG and Agent in Practice: Two Paths for LLM Integration
Starting from LLM integration, this article covers two paths: local Ollama deployment and Alibaba Cloud Bailian cloud API calls, detailing Bailian registration, API Key creation, free quota management, and overspend protection — laying the groundwork for RAG and Agent practice.
Tencent MiaoYing Agent Hands-On: One Canvas for the Entire AI Video Workflow
Bilibili creator tests Tencent MiaoYing Agent: enter an idea, and the Agent auto-generates story, character, and storyboard cards and batch-creates video, all edited and exported on one canvas.
LangChain Beginner's Guide: The Core Framework for Agent and RAG Development
What is LangChain? This article based on a Bilibili tutorial outlines LangChain's core positioning, the three major model limitations it solves (knowledge timeliness, external interaction, state persistence), and the official documentation learning path to help developers quickly get started with Agent and RAG development.
NVIDIA OpenShell: Putting the Brakes on AI Agents
NVIDIA open-sources OpenShell, an Agent security platform using an OS-level sandbox and the Sentry network chip as dual defenses to cage AI Agents. This article breaks down the technical principles, adversarial test results, and real shortcomings of the Alpha stage.
LangChain from Scratch: A Deep Dive into a Hands-On RAG and Agent Tutorial
A deep dive into a Bilibili zero-foundation LangChain tutorial: analyzing the learning path around RAG and Agent scenarios, from basic calls to complete deployable projects. Suitable for students, career changers, and side-project developers.
The State of Context Engineering: The Paradigm Shift from Prompting to Context Management
Drawing on dbreunig's article and Hacker News discussion, this piece maps the boundaries, current practices, and open questions of context engineering, and how it differs from prompt engineering.
OpenAI Dots vs Anthropic Claude Duet: The AI Assistant Rivalry Escalates
Anthropic's Claude Duet joins OpenAI Dots and Meta Muse in a new AI assistant rivalry. We analyze their positioning, cloud execution, and sensitive-action approval.
WorkBuddy Complete Beginner's Guide: A Full Breakdown of the Interface and Features, from Getting Started to Hands-On Practice
How to use Tencent WorkBuddy? Based on an ultra-detailed Bilibili tutorial, this article breaks down WorkBuddy's interface layout, workspace, assistant, projects, experts, skills, MCP connectors, scheduled tasks, and knowledge base to help beginners quickly get started with the AI office workbench.
Tiltmeter: Open-Source Tool Monitors Third-Party API Changes for Agents
Tiltmeter is an open-source tool that monitors third-party API response structure changes, helping Agents like LangGraph check for drift before trusting data, with automatic code fixes.
Completion or Agent? One Formula Explains the AI Coding Paradigm Divide
What's the real difference between completion and Agent? One formula—Agent = Model + Harness—explains the AI coding paradigm: completion guesses the next line, Agent reads the repo, edits multiple files, runs tests, and self-corrects. Includes selection criteria and practical usage tips.
LangChain for Beginners: A Practical Guide to Structured Output and Agents
Starting from zero with LangChain: clarify the difference between low-code platforms and large model application development, covering structured output, tool calling, Agent practice, and multi-tenant RAG enterprise deployment—ideal for engineers with development experience looking to transition into AI application development.
Only Three Agent Recommendations for Beginners: ZeroStack, Claude Code, and DeepSeek Harness
Bilibili creator recommends three beginner Agents: ZeroStack for lightweight devices, Claude Code with a mature ecosystem, and DeepSeek Harness for easy plugin integration. This article outlines use cases and practical tips for each tool.
DeepSeek Harness Step-by-Step Installation Guide: Core Principles and Building Automated AI Applications
Based on Bilibili creator Pan Ge's DeepSeek Harness tutorial, this guide covers Node.js installation, npm global directory and cache configuration, environment variables, and the core principles of Harness with Agents.
Gemini 4 Argon Launches Globally: Key Highlights from the AI Daily Brief
Google opens Gemini 4 Argon globally across Pro and Ultra subscriptions and the API, and demonstrates robot control. This article rounds up open-source models, Agent infrastructure, cost transparency, and safety governance updates.
From Vibe Coding to AI-Automated Research: How Agents Are Reshaping the Research Workflow
From Vibe Coding to Coding Agent to AI-automated research, we analyze how Agents intervene in literature review, data analysis, and experiment execution, and which judgment tasks remain irreplaceable for researchers.
Needle: An Agent-Native Outbound Engine Powered by Claude/ChatGPT/Grok Prompts
Needle is an agent-native outbound engine that lets you find and reach ideal customers on LinkedIn, Instagram, and email via Claude, ChatGPT, or Grok prompts. This article analyzes its positioning, agent-native design logic, and key details missing from the launch.
Deconstructing Coze 3.0 Agent Core Capabilities: From Beginner to AI Talent in Three Months
Deconstructing Coze 3.0 agent core capabilities: a three-step learning path from prompt engineering and RAG knowledge bases to multi-agent practice, plus a rational look at three-month employment promises.