AI Agent Hub: A Complete Path from Concept to Production
An AI agent hub covering core concepts, hands-on tutorials, framework and platform selection, MCP tool integration, browser control, memory design, failure triage, and governance.
- 20 articles
- 6 wiki entries
- 4 tools
Learning agents is not about collecting terminology. It is a path you can actually finish: understand how an agent differs from a workflow, build a minimal version that runs, choose a framework for your scenario, then add memory, permissions, and failure handling. This hub arranges our content in that order.
Who is this hub for?
On this page
What is an AI agent
Start with the concepts, the capability boundary, and the common patterns.
- Wiki
Agent
Wiki entry: definition, components, and typical uses
- Wiki
Tool Calling
Tool calling: the prerequisite for taking action
- Wiki
AI Workflow
Where workflows end and agents begin
- Article
Why AI's Momentum Is Shifting to Agents: From Chat Windows to Software That Gets Things Done
Agents are no longer limited to automated clicks in demo videos. They are redefining the interface to software across e…
- Article
ReAct vs. Plan-and-Execute vs. Reflection: Three Agent Patterns Explained
ReAct thinks and acts one step at a time, Plan-and-Execute plans before moving, and Reflection checks the work afterwar…
Build your first agent
Start minimal: tool calls, task flow, and both no-code and self-built routes.
- Article
Build an AI Agent from Scratch: A Complete Guide to Tool Use, Memory, and Workflows
Use a realistic research-assistant project to understand goal planning, tool calls, memory management, result validatio…
- Article
Build a Useful AI Agent Without Code: A Complete Dify Tutorial
Follow a realistic customer-support scenario to configure a model, connect a knowledge base, add tools, orchestrate a w…
- Article
MCP Getting Started: A Minimal Viable Approach to Connecting AI with Tools and Data Sources
Using a todo list and document query case study, this guide clarifies MCP's role, server architecture, tool definitions…
- Article
Building an MCP Server from Scratch: A Hands-On Guide to File Search Tools
Build a file-search-capable MCP Server in roughly 100 lines of TypeScript, ready for immediate use in Claude Code and C…
- Article
n8n + AI Automation Workflow Tutorial: Turning Repetitive Tasks into a Seamless Automated Pipeline
Using the real-world scenario of 'automatically organizing daily emails and generating summaries,' this guide walks you…
Choosing a framework or platform
Where LangGraph, AutoGen, CrewAI, Dify, Coze, Flowise, and n8n each fit.
- Article
The Ultimate 2026 Comparison of AI Agent Frameworks: LangGraph, AutoGen, CrewAI, and LlamaIndex Workflows—Which Is Best for Production?
We compare leading agent frameworks across state management, multi-agent collaboration, tool calling, observability, an…
- Article
The Ultimate 2026 Comparison of AI Agent Build Platforms: Which Is the Best Choice Among Dify, Coze, Flowise, n8n, and AutoGPT?
A comparison of the practical implementation value of Dify, Coze, Flowise, n8n, and AutoGPT across dimensions such as v…
- Article
Are Multi-Agent Systems Really Useful? When Not to Use Multiple Agents
Multiple agents collaborating sounds more capable than one, but many multi-agent systems are simply slower, more expens…
- Wiki
A2A
A protocol for agent-to-agent collaboration
MCP: connecting tools and data
How the protocol works, MCP versus function calling, useful servers, and the risks.
- Wiki
MCP
Wiki entry: what MCP is
- Article
MCP vs. Function Calling: Which AI Tool Invocation Approach Should You Choose?
Function calling is a model capability, while MCP is a tool distribution protocol; they operate at different layers and…
- Article
Diagram of the Relationship Between MCP Clients, Hosts, and Servers
Reading the MCP documentation often leaves readers confused by the terms 'Host,' 'Client,' and 'Server.' This article u…
- Article
10 Types of MCP Servers Every Developer Should Know
The MCP Server ecosystem is exploding, but only a handful of categories are useful to developers every day. This guide …
- Article
MCP Security Risks: Permissions, Data Leaks, and Erroneous Tool Invocations
Connecting an AI to an MCP Server is akin to installing a plugin capable of reading from and writing to real-world syst…
Browser and computer use
How tools like Browser Use drive a page, and how the main options compare.
- Article
How Browser Agents Interact with Web Pages: Screenshots, DOMs, and Action Loops
Enabling AI to click through web pages, fill out forms, and book flights relies on a 'observe → decide → act → re-obser…
- Article
The Ultimate 2026 AI Browser Automation Review: Browser Use vs. Stagehand vs. Playwright AI vs. Puppeteer
A hands-on comparison of Browser Use, Stagehand, Playwright AI, and Puppeteer across web automation, reliability, debug…
- Wiki
Computer Use
Letting a model operate a computer directly
Memory, failure, and governance
The hard part after launch: what to remember, why runs go wrong, and how far permissions go.
- Article
How Should Agent Memory Be Designed? Short-Term, Long-Term, and Vector Memory
Agent memory is not simply a record of every conversation. This guide separates memory into task state, cross-session l…
- Article
Eight Reasons Agent Tasks Fail—and How to Troubleshoot Them
When an Agent runs away, stalls, or returns the wrong answer, which layer actually failed? This guide groups eight caus…
- Article
Why AI Agents Lose Control: Tool Permissions, Memory Contamination, and Task Boundary Design
Agent loss of control is not a science fiction problem but an engineering one: overly broad tool permissions, injection…
- Article
Agent Governance Guide: Set Boundaries Before AI Starts Taking Action
Agents can call tools, read and write data, and execute operations, so governance must begin during system design rathe…
Tools you can try now
Agent-related products in our directory, plus related sections.
- Tool
AgentGPT
A revolutionary AI platform! Auto-GPT with a user-friendly interface.
- Tool
Replit Agent
An AI-powered application development agent for Replit that automatically writes code, debugs, and deploys projects bas…
- Tool
Gemini CLI
Google's open-source command-line AI agent that integrates Gemini's long-context capabilities into terminal-based devel…
- Tool
LangChain
An LLM framework for building and deploying AI applications
- Section
AI Wiki
The full index of agent, MCP, and tool-calling entries.
FAQ
- Q: How is an AI agent different from an automated workflow?
- A: A workflow follows steps a human wrote down; an agent lets the model decide which tool to call next. When the path is fixed, a workflow is cheaper and more predictable. An agent is only worth its unpredictability when the path has to be decided at run time. See our piece on agents losing control and the AI workflow wiki entry.
- Q: Should a first agent start from a framework or a no-code platform?
- A: Get the flow running on a platform such as Dify first and confirm the task is worth automating. Only then decide whether to rebuild it on LangGraph or AutoGen. Most teams stall on unclear task boundaries, not on framework limits.
- Q: Is a multi-agent setup always better than a single agent?
- A: No. Multiple agents multiply context-passing cost and debugging effort. They pay off only when roles are genuinely separate and a single agent's prompt can no longer hold the job. Our multi-agent article works through the trade-off.
- Q: What risk is most often overlooked when granting an agent tool access?
- A: Write permissions and memory poisoning. A faulty read tool produces a wrong answer; a faulty write tool damages real data, and poisoned long-term memory keeps affecting later tasks. See our MCP security and agent memory articles.