Guides
Guides to working with AI agents
What an agent is, how it uses your team's tools and what waits for approval. Every guide has sources and a date.
AI agents for teams: how people and AI agents work in one chat
What an agent needs, who answers in the chat, what waits for a person and what it costs.
Read the pageAll guides
AI agent examples: 20 tasks you can hand to an agent at work
20 AI agent examples at work, by team: the tool each one uses, the access it needs, and which actions wait for a person to approve them.
How to create an AI agent for your team: role, instructions, tools, budget and owner
A checklist for creating an AI agent for your team without code: the task, instructions, tools, approvals, budget and owner, then the steps in agentes.chat.
Human-in-the-loop AI agents: how approvals for sensitive actions work
Which actions an AI agent should take alone and which should wait for a person, plus how approvals, permissions, budgets and audit trails fit together.
MCP connectors explained: how AI agents use your tools
What MCP (Model Context Protocol) is, what an MCP server does, how one-click sign-in works, and how to give each AI agent only the tool access it needs.
What are AI agents? A plain guide for teams
What AI agents are, how they work, how they differ from chatbots and agentic AI, the main types, and what teams actually use them for at work.
Which official MCP servers support one-click sign-in? (2026 check)
We checked which official remote MCP servers accept OAuth sign-in with dynamic client registration, server by server, with method, date and source for each.