GuidesAI and agents
An AI agent that drives a browser: useful, slow and to be kept on a leash
The loop
- 1LookScreenshot or page structure.
- 2DecideThe model picks the next action.
- 3ActClick, type, scroll.
- 4CheckNew screenshot, and so on.
Browser or API
API
Driven browser
Safety rules
| Rule | Why |
|---|---|
| Isolated browser | No access to your personal accounts |
| Allowlist of sites | The agent does not wander off |
| Confirmation before purchase or sending | A booby-trapped page does not decide |
| Step budget | A stuck loop stops |
| Screenshots recorded | Understand what happened |
The basics: the AI agent loop. The risks: prompt injection.
Frequently asked questions
- How does the agent see the page?
- Through screenshots, through the page structure (accessibility tree, DOM), or both. The model then decides the action: click, type, scroll.
- Is it reliable?
- Less than an API. A pop-up, a button that moves or a captcha can block the agent. Plan for retries and a check of the result.
- What are the risks?
- A page can contain hidden instructions that hijack the agent. Use it in an isolated browser, with no personal sessions logged in, and with confirmation before any purchase or message.