Stop approving every command: put your AI agent in a container

Description and use

<p>If you've used a coding agent for more than a day, you know the rhythm.</p> <p>It writes a command. It stops. It asks you to approve. You click yes.<br> It writes another command. It stops. It asks again.</p> <p>By lunchtime you've clicked yes forty times, and you've quietly stopped reading what you're approving. At<br> that point the safety feature isn't protecting anything. It's just slowing you down.</p> <p>There's a way to get the safety without the clicking, and it isn't a setting. It's <em>where you run the agent</em>.</p> <h2> What the approval prompt is really for </h2> <p>The promp

Problem

<p>If you've used a coding agent for more than a day, you know the rhythm.</p> <p>It writes a command. It stops. It asks you to approve. You click yes.<br> It writes another command. It stops. It asks again.</p> <p>By lunchtime you've clicked yes forty times, and you've quietly stopped reading what you're approving. At<br> that point the safety feature isn't protecting anything. It's just slowing you down.</p> <p>There's a way to get the safety without the clicking, and it isn't a setting. It's <em>where you run the agent</em>.</p> <h2> What the approval prompt is really for </h2> <p>The promp

Outcome

<p>If you've used a coding agent for more than a day, you know the rhythm.</p> <p>It writes a command. It stops. It asks you to approve. You click yes.<br> It writes another command. It stops. It asks again.</p> <p>By lunchtime you've clicked yes forty times, and you've quietly stopped reading what you're approving. At<br> that point the safety feature isn't protecting anything. It's just slowing you down.</p> <p>There's a way to get the safety without the clicking, and it isn't a setting. It's <em>where you run the agent</em>.</p> <h2> What the approval prompt is really for </h2> <p>The promp

Evidence

Stop approving every command: put your AI agent in a container

Source