How much control should AI agents have over your terminal?

While building Vrykell, one question kept coming up: how much control should an AI agent actually have over your terminal?

Most AI coding tools operate in their own environment. But when I'm debugging a build failure on a remote server, I don't want to keep copying errors between my terminal and a chat window.

I want the agent to work with the terminal I'm already using, whether it's local or connected over SSH.

That's why Vrykell binds conversations to specific terminal sessions and preserves command output, working directories, git branches and exit codes.

But giving an agent access to a real machine also raises questions about trust and control.

I'm curious how other developers approach this:

• Would you let an AI agent execute commands directly on your local machine or SSH server?

• Would you prefer approval for every command, only potentially destructive commands, or fully autonomous execution?

• Do you prefer agents working in isolated sandboxes, or in your actual development environment?

I'm building Vrykell around explicit execution targets and user-controlled permissions, but I'd love to hear how others think about this tradeoff.

What would make you comfortable giving an AI agent access to your terminal?