Let the agent browse in its own browser, or in your Chrome or Edge with your logins through the Suzent extension.

How your agent reads documents, creates and edits files, and finds files by name or content.

How Suzent asks before it acts, the three permission modes, and how to remember your answers.

How the agent asks you a focused question, shows tables, forms, and buttons you can click, and sends messages through your chat apps.

Connect tools from any MCP server, by URL or by the command that starts it, and choose which conversations use them.

Generate and edit images, read pictures, make videos, and have the agent speak, plus the models each one needs.

智能体能做什么，如何选择一个对话可以使用哪些工具，以及每类工具的详细说明在哪里。

How your agent runs commands, where they run, background commands, and which commands need your approval.

How the agent hands work to helper agents, what helpers can do, and how you watch, redirect, or stop them.

How the agent breaks work into tracked tasks, how the project board works, and how it schedules its own follow-ups.

How the agent searches the web and reads pages, how to use your own SearXNG instance, and where to follow along.