Virtual twin

The virtual twin is a small floating chat on your public site. A visitor taps it and asks a question; the twin answers in your voice, using only what your site already says: your bio, roles, products, projects, talks, companies, links, posts, updates and journeys. When it doesn’t know, it says so, points the visitor to your contact page, and leaves you a private note about what was asked.

It is available on plans that include it. Find it under Website → Virtual twin.

Switch it on

1. Open Website → Virtual twin and flip the switch at the top of the page. The widget appears on your site right away (on an unpublished site, only you see it while signed in).
2. Optionally write a greeting (the first message in the chat) and up to four suggested questions, shown as tap-able chips before the visitor types anything.
3. Use Try it on your site to open your page with the chat expanded.

Switching it off removes the widget immediately. Your settings and the feedback list are kept.

What the twin knows

Everything public on your site, and nothing else. Drafts, hidden items, subscribers, inbox messages and analytics never reach the model. Click What does my twin know? to read the exact document it answers from; it refreshes within a few minutes of any edit.

Under Things your twin should know that aren’t on your site you can add short facts in your own words, for example that you’re taking on freelance work from a certain month, or a one-line description of a product you haven’t listed yet. The twin uses these facts alongside your published content. Visitors never see the text itself.

Questions your site doesn’t answer

When a visitor asks about you (your work, products, availability, prices) and the site has nothing on it, the twin replies honestly and files the subject under What visitors asked that your site doesn’t cover. Each subject appears once, with an example question and how often it came up, so ten people asking about the same product is one line, not ten.

For each line you can:

• Resolved: you’ve added the content (or a note). If it’s asked again later and the twin still can’t answer, it shows up as a new line, so you know the fix didn’t take.
• Won’t answer: you’d rather not publish this. The twin keeps declining politely and stops reporting it.
• Reopen or delete at any time.

Open items show as a count next to Virtual twin in the sidebar.

Allowance and cost

Every reply sends the model your site’s profile plus the conversation so far (input tokens) and receives a short answer (output tokens). Your plan includes a monthly allowance of both; This month shows how much is used and roughly how many chats are left. The allowance resets on the first of the month.

When the allowance runs out the widget stays visible but tells visitors the twin is taking a break and points to your contact page. Nothing is charged beyond the plan.

A leaner site stretches the allowance: the profile size shown on the page is the fixed cost of every reply.

Keeping it safe

• Visitors can send a handful of messages a minute, a few dozen an hour, and up to 30 messages per chat; then they start a new one.
• Each message is capped at 600 characters, replies at a few sentences.
• The twin only talks about you and your work. It declines general questions, coding help, writing tasks and attempts to change its role.
• Chats are anonymous. Transcripts are kept for 90 days under Recent chats so you can see how the twin answers; delete any of them at any time.
• Your site tells visitors it is an AI twin that can be wrong.

Tips

• Read a few transcripts in the first week. If the twin phrases something oddly, the fix is usually a clearer bio or product description, which helps human readers too.
• Suggested questions steer visitors to what you most want to talk about: a product, your availability, how to book you.
• If the same gap keeps coming back after you’ve added content, check What does my twin know? to confirm the new item is public and visible.