Is it safe to let an AI edit my site?

Why it’s safe

Every change lands on a draft first. The AI doesn’t type into your live site. It works on a private copy, you get a preview link, and you see exactly what visitors would see before any of it counts.

Who can press publish depends on which AI you’re using. This is the part worth getting right rather than glossing:

• Bernard in your dashboard cannot publish. He edits the draft; you press Approve on the preview page, signed in to your account. That one is structural - there’s no way round it.
• Your own connected AI can publish, when you ask it to. If you’ve connected ChatGPT, Claude or Gemini, it acts with your authority - that is what connecting it means - so it can make a draft live exactly as you would. It’s instructed to do that only when you ask, and never on its own initiative.

If you want the arrangement where nothing reaches the public without your press, use Bernard in the dashboard. If you want your own AI to finish the job when you say “yes, put it live”, connect it. Both are reasonable - they’re just different, and you should get to choose knowingly.

No code goes on your site without passing bernard’s checks. If bernard moved your site across, the tools it was already running came with it - your analytics, your booking widget, an embedded map. That’s deliberate: they’re part of how your site works. What’s locked down is editing. Every write goes through a guard that strips or rejects any new or altered script, so no edit - by you, by Bernard, by a connected AI - can sneak in tracking, pop-ups or code nobody checked. There are three exceptions. The first is a short list of checked tools, such as diagrams, charts and full-screen photos, which bernard runs at a version it pinned and which collect nothing about your visitors (Embed a calendar, a diagram, a chart or another tool on my site). The second, on every account, is code your assistant writes for something bernard has no ready-made part for, such as a calculator. bernard checks that code before it goes into your draft: that it does not load code from other websites, that it talks only to the places it names, that it does not send anything until a visitor does something, such as pressing a button, and that it does not use tricks to recognise or follow your visitors. Code that fails is not put on your page. Code that passes waits in your draft, the summary of the change says what it talks to, and it reaches visitors only when you publish (Can I run my own code on my site?). The third, on every site, is bernard’s own library of animations, which goes through the same checks and is also tried in a real browser by bernard’s own tests (Is it safe to let bernard add code to my site?). Your site’s own pages are also served from their own address, kept apart from your bernard dashboard, so nothing on them can reach your account.

Everything is recorded, and everything is reversible. bernard keeps the last 100 published versions of your site - every change with a plain-English reason, every publish noting what went live and whether it came from you or your assistant. Restore any of them from your dashboard, or just ask the AI to put it back. For anything older, bernard support can recover your site from backups kept up to a year. This, rather than the AI being incapable, is what actually protects you.

The key is small and revocable. It covers your own sites and nothing else, and replacing it in Account → Your AI revokes the old one instantly. Treat it like a password: someone holding it could edit your drafts and publish them - replacing it is the kill switch that stops them dead, and the history is there to undo anything they did. See What is the connection key?.

Safety works in both directions, too: bernard doesn’t just guard against bad changes - he actively watches for problems. Every time you publish, your site is re-checked for broken links, missing page details and anything Google would struggle to read, and every fix is re-checked after it goes live. How that works is covered in How Bernard checks your site - and what he does about it.

Safety is also about your data, not just your pages: what bernard holds, where it lives, and what the AI does and doesn’t do with it. That’s covered in What does bernard do with my data, and is it GDPR-compliant?.

And safety runs one more way - towards the people who visit you. What’s running on your site that watches or counts them is listed in What’s tracking my visitors on my site?, and why some of it has to be asked about first is in What are cookies, and why does my site need a banner?.

And sometimes safety means the website is not for everybody. A whole site can be made invitation-only, so ordinary visitors and search engines meet a sign-in door and only the people you invited get through - see Make my whole website private for invited people.

Safety starts at the door to your own account, too. You can make bernard ask for a code from an app on your phone each time you sign in, so a stolen password or a borrowed inbox is not enough to get in - see How do I make my bernard sign-in safer with a code from my phone?.