# AI agents, explained

Short, plain answers to the questions people ask before they hand work to an AI agent.

Updated 2026-11-18. Page: https://casama.ai/learn/

- [AI agent vs chatbot: what's the difference?](https://casama.ai/learn/ai-agent-vs-chatbot.md): A chatbot answers in a text box. An AI agent has tools, a place to work, memory and a schedule, so it does the task itself. A side-by-side table.
- [Are there free AI agents?](https://casama.ai/learn/are-there-free-ai-agents.md): Yes. Open-source AI agents are free to run and some hosted ones have free plans, but the AI model usually costs money unless you run one locally.
- [Can AI agents run on my own models?](https://casama.ai/learn/can-ai-agents-run-on-local-models.md): Yes. An AI agent can use a local model through Ollama, LM Studio or vLLM if the agent software accepts an OpenAI-style endpoint. What works and what doesn't.
- [How do AI agents work?](https://casama.ai/learn/how-do-ai-agents-work.md): An AI agent runs a loop: the model picks a step, a tool carries it out, the model reads the result and picks the next step, until the task is done.
- [How much does an AI agent cost a month?](https://casama.ai/learn/how-much-does-an-ai-agent-cost.md): From $0 for free software and a local model, to $15 to $200 a month for most hosted AI agents. What you pay for, and the published prices of 17 agents.
- [How do I self-host an AI agent?](https://casama.ai/learn/how-to-self-host-an-ai-agent.md): To self-host an AI agent you need a machine with Docker, an AI model key or a local model, and about 15 minutes. The steps, with Casama as the example.
- [Is it safe to give an AI agent access to my email and accounts?](https://casama.ai/learn/is-it-safe-to-give-an-ai-agent-access-to-my-email.md): It can be, if the agent asks before sending, can't see your passwords, treats message content as untrusted, and you can see and undo what it did.
- [Is OpenClaw safe, and is it free?](https://casama.ai/learn/is-openclaw-safe.md): OpenClaw is free and MIT-licensed. It can be run safely, but its sandbox and approvals are off by default. What that means, and how to set it up more safely.
- [How do I run AI agents on my own server from my phone?](https://casama.ai/learn/run-ai-agents-on-your-own-server-from-your-phone.md): Run the agent software on a computer at home, give it an address your phone can reach without port forwarding, and sign in with a native app.
- [Self-hosted or hosted AI agent: which should you choose?](https://casama.ai/learn/self-hosted-or-hosted-ai-agent.md): Host it yourself for control over data, models and cost. Use a hosted agent for no setup and no upkeep. A table of trade-offs and a way to decide.
- [What is a computer use agent, and which ones let you take over?](https://casama.ai/learn/what-is-a-computer-use-agent.md): A computer use agent works a computer the way you do: screen, mouse, keyboard, browser. Where it runs, why it matters, and which agents let you watch and take over.
- [What is an AI agent?](https://casama.ai/learn/what-is-an-ai-agent.md): An AI agent is software that uses an AI model to carry out a task step by step with tools, instead of only answering. Examples, limits and how it differs from a chatbot.
- [What is an AI employee?](https://casama.ai/learn/what-is-an-ai-employee.md): An AI employee is an AI agent given a standing job, with tools, memory, a schedule and limits. What AI workers and AI interns can do, what they cost, and where they fail.
- [What is an AI teammate?](https://casama.ai/learn/what-is-an-ai-teammate.md): An AI teammate is an AI agent that stays: it has a role, remembers your work, starts tasks without being asked and works alongside people.
- [What is MCP, and what is an MCP client?](https://casama.ai/learn/what-is-mcp.md): MCP (Model Context Protocol) is a standard way for AI apps to use outside tools and data. A server offers tools; a client is the AI app that uses them.
- [Which AI agents ask before they act?](https://casama.ai/learn/which-ai-agents-ask-before-they-act.md): Most AI agents ask before some actions. They differ in which actions, whether you can set the rules, whether payments always ask, and whether you can undo.
- [Which AI agents don't train on your data?](https://casama.ai/learn/which-ai-agents-dont-train-on-your-data.md): Which AI agents say they don't train on your data, which train by default until you opt out, and which don't say. Seventeen agents checked, with sources.
- [Which AI agents have iPhone and Android apps?](https://casama.ai/learn/which-ai-agents-have-iphone-and-android-apps.md): Which AI agents have real phone apps, which are in early access, and which you reach through chat apps instead. Seventeen agents checked, with sources.
- [Which AI agents let you choose the model or use your own API keys?](https://casama.ai/learn/which-ai-agents-let-you-choose-the-model.md): Open-source AI agents usually take your own API keys, subscriptions and local models; hosted ones usually pick for you. Seventeen agents checked, with sources.
- [Which AI agents can run tasks on a schedule?](https://casama.ai/learn/which-ai-agents-run-tasks-on-a-schedule.md): Most AI agents can run on a schedule now. They differ in what else can start them, the limits, whether your computer must stay on, and what still asks first.
- [Why give an AI agent its own computer?](https://casama.ai/learn/why-give-an-ai-agent-its-own-computer.md): An AI agent with its own computer works apart from your devices, keeps going while you're away, keeps its files and sign-ins, and can be rolled back.
