#AI Agent
1073 related articles
Amp Leans on OpenAI Models to Take AI Agents Beyond Code
Amp team reveals its AI Agent vision: beyond coding, covering the full workflow. OpenAI models handle most tokens, Sign in with ChatGPT boosts quota, and super-fast models plus email automation point toward general work agents.
Handing the Shop to an AI Agent for Seven Days: A Real Experiment with Zero Human Intervention
A creator hands his real shop to an AI Agent for seven days: automatic orders, customer replies, inventory and pricing, with only approvals over $50. Errors are preserved, and the ledger, guardrails and decision audit are fully shown.
ChatGPT vs. AI Agents: Choosing Between Conversation and Agentic Workflows
ChatGPT vs. AI Agent explained: the real difference between basic conversation and agentic workflows, the observe-choose-act-check loop, and when to use each.
AI Agent Calls Real SolidWorks: An Open-Source Modeling Assistant for STEM Students
An open-source GitHub project with 1.3k stars lets an AI Agent call real SolidWorks to create 3D models, assemblies, and drawings, with result validation built in.
Six Types of AI Agents Explained: A Guide to Deploying and Choosing Open-Source Agents
A systematic breakdown of six open-source AI agents—OpenClaw, Hermes, Agent Zero, OpenHands, Paperclip, and Buzz—covering their underlying architectures, pros and cons, plus VPS deployment and selection advice.
The Five Permission Levels of AI Agents: From ChatGPT Q&A to Fully Autonomous Agents
Break down AI agent permissions into five levels: from ChatGPT pure conversation, project documents, MCP connectors, Computer Use automated clicking, to unattended agents—analyzing capability boundaries, prompt injection risks, and approval fatigue level by level, with three practical rules: read-only by default, manual confirmation for irreversible operations, and per-project isolation.
How to Choose an AI Agent? Dots, Muse, Grok Bot, and Claude Duet Compared
Compare OpenAI Dots, Metamuse, Grok Bot, and Claude Duet AI Agents: Dots integrates with Slack/Teams, Muse has a free tier, Grok Bot suits cross-tool tasks, and Claude Duet is US waitlist-only.
How Is an AI Agent Different from a Chatbot? A Complete Explanation
What's the difference between an AI Agent and a chatbot? This article breaks down the Agent's work loop—receiving goals, autonomous planning, calling tools, and reporting results—clarifying the essential difference in how tasks are executed.
How Does ChatGPT Check the Weather? The AI Agent Tool-Calling Loop Explained
ChatGPT's training data is outdated—so how can it answer real-time weather queries? This article breaks down the AI Agent tool-calling loop: how models generate tool requests, how code executes and feeds back results, and the engineering logic behind the definition of an Agent as "model + tools + loop."
ChatGPT Isn't an Agent? A Clear Explanation of What AI Agents Really Are
Are ChatGPT, Gemini, and Claude really AI Agents? This article starts from the definition of an Agent, distinguishes Agentic AI from true Agents, and reviews the evolution from rule-based chatbots to autonomous agents to help clarify the concepts.
Claude Code Deep Configuration Guide: From Model Selection to Skills in Practice
Based on Tech With Tim's three-hour hands-on course, a systematic walkthrough of Claude Code's model and effort level choices, permission modes, CLAUDE.md conventions, Skills scoping, subagents and Hooks configuration, plus advanced usage like context compaction and parallel sessions—helping you turn a default install into a genuinely efficient workspace.
748-Episode AI Agent Development Course on Bilibili: A Complete Guide from Beginner to Enterprise-Level Practice
Breaking down the 748-episode AI Agent development course on Bilibili: Fundamentals covers LLM principles and API calls; Advanced covers RAG, Tool Use, memory management, and multi-agent collaboration; Practical covers intelligent customer service, office automation, and more—plus learning paths and pitfalls to avoid.
Claude Duet Takes the Initiative: AI Agents Start Watching Things for You
Baiya AI Daily: Claude Duet's Opus 5.5 brings proactive reminders but background polling eats subscription quota; Tipo caching extended to 12 hours, OpenAI discloses GPT 5.6 finding PHP flaws and new model routing rules, Walmart uses an agent gateway to put brakes on AI orders.
Claude Duet In-Depth Review: The Most Proactive AI Personal Assistant Has Arrived
Claude Duet is Anthropic's personal AI assistant with scheduled proactive checks, Artifacts dashboards, and email drafting. A hands-on review of its core features, Uber booking failures, and how it compares with Grokbot, Muse, and ChatGPT Dots.
Claude Duet Research Preview Launches, Fable 5.5 Release Imminent | AI Daily
AI Daily: Anthropic opens Claude Duet research preview with cloud task execution and human approval for payments and deletions; Fable 5.5 release imminent; three OpenAI models enter Google Cloud Model Garden; Ant Digital's LingDT saves over 90% tokens; China Telecom open-sources Xingchen intent model; ElevenLabs opens real-time speech translation in 90 languages.
Claude Duet Hands-On Review: The Most Proactive Personal Agent — Full Analysis of Its Strengths and Weaknesses
Hands-on review of Claude Duet: Anthropic's most proactive personal agent, with built-in check-ins, writing style learning, and a skill system — but no cloud browser control or local skill management. Compared with Grokbot, Muse, and ChatGPT-Dots.
Coze Studio Open-Source Private Deployment in Practice: Building AI Workflows with CentOS 7 + Docker
A complete walkthrough of Coze Studio open-source private deployment: CentOS 7 VM + Docker setup, Ollama model configuration, Agent and knowledge base building, custom plugin development, and Chat API/SDK integration, plus an analysis of feature trims versus the online version and selection boundaries.
WorkBuddy Step-by-Step Guide: Build Your Own AI Agent Work Assistant
WorkBuddy step-by-step guide: starting from the limits of chat models like Doubao, learn to build your own AI Agent work assistant for batch local file processing and automation—no programming required.
MCP Protocol Explained in One Minute: Let Your AI Agent Actually Call Tools
Understand MCP (Model Context Protocol) in one minute: how Host, Client, and Server collaborate so AI apps can call real tools through a standardized interface, with servers written once and reused by any MCP client.
AI Agents Aren't Chat Boxes: Breaking Down the Plan-Tool-Read-Decide Loop
An AI Agent isn't a smarter chatbot but a four-step loop: plan, call tools, read results, decide. This breakdown uses an 18KB file task to explain the mechanism, compares Claude Code, Codex, and ChatGPT tool calling, and summarizes traps like infinite tool loops and blind trust in tool output, plus five convergence practices.