These docs describe the current Dante AI platform. On the earlier platform? Your API reference is api-v2.dante-ai.com/openapi.json, and your key goes in the x-api-key header.

Publish your agent

Save, put it on your site, update the live agent: the three actions on the Deploy page, the embed snippet, allowed domains, the live-status check, and the paid switches.

Open your agent's Publish page →

The welcome message

On the Setup tab, the welcome message is the first thing visitors see when they open the chat. Write a short greeting in your agent's voice, for example a sentence or two that says who you are and invites the visitor to ask a question.

• You can use up to 1000 characters. A live counter under the box shows how much you've used, and the box stops you at the limit so a long greeting always saves cleanly.
• If a save is ever rejected, the message under the box tells you exactly what to fix, instead of a generic error. Your edits stay in place and Save changes stays available, so nothing is lost.

Suggested questions and launcher teasers

On the Setup tab you can add quick replies: short suggested questions a visitor can tap instead of typing. They appear in two places:

• Inside the chat panel. Every quick reply you add is shown as a tappable chip, so visitors always see the full list once the chat is open. The chips lay out as a compact wrapped row rather than a stacked list, so a longer set stays readable without pushing the conversation down the panel, and the whole group settles in together instead of arriving one at a time.
• Beside the closed launcher. When Launcher tooltips is on, the first two quick replies also float as teaser bubbles next to the launcher icon before the visitor opens the chat, with a small unread count on the launcher that matches the number of bubbles shown. Keeping the floating stack to two bubbles stays unobtrusive on your site, so put your two strongest questions first in the list.

Tapping a teaser bubble or a chip sends that question straight to your agent. Visitors can dismiss the floating bubbles; they reappear for returning visitors after a day.

Your quick replies stand on their own. They show whenever you have added at least one, whatever else is switched on, and the AI follow-up suggestions toggle does not affect them: that setting only controls the extra questions your agent writes for itself after it has answered. The list you author on the Setup tab is the one visitors see at the start of every conversation. This is true on every install, whether you use the floating launcher script or drop the agent into your page as an iframe. Once your agent is live, press Update live agent after editing the list, since that is what pushes the change to your live site.

Where the first set comes from

You do not start from an empty list. While your website is being read during setup, Dante AI writes a starting set of quick replies from your own content, along with a suggested agent name and behaviour, so the very first chat you try already asks questions your agent can answer. They appear as soon as the first page has been read, which is why they can arrive while you are still on the setup screen.

Behaviour and model

The Model tab controls how your agent answers. Pick a personality preset from the dropdown, or type your own instructions straight into the Behavior box: its tone, what topics to cover, and what to avoid. The Behavior box is always editable here, so you can refine the wording whenever you like, and Save changes turns active as soon as you make an edit. Saving stores your behaviour and model edits as a draft (see Save, install, update below).

The same tab is where you choose the AI model that powers your agent's replies. See AI models for how the models differ and what each one costs.

Save, install, update

The Deploy page does three different things, and you only ever press two of them at a time. The buttons under the page title change with the state your agent is in, and the line beneath them always says which state that is.

• Save changes. Stores your setup, model, appearance, and behaviour edits as a draft inside Dante AI. Nothing on your website moves. Visitors still see whatever was last live, so you can keep working until you are happy with it.
• Copy embed code. The first time, putting your AI agent on your website means copying the snippet and pasting it into your site. There is no button that can do that step for you. The snippet stays on the Install tab afterwards for a second site or a new domain.
• Update live agent. Once your agent is live, this pushes your saved edits to the agent on your website. Visitors see the change on their next page load, and you can undo it in one click.

What the page shows in each state

The status line is the truth. Live on your site ✓ only appears once a real visitor has loaded a page carrying your snippet; nothing you press inside Dante AI can turn it green. The amber not on your website yet line links straight to the Install tab.

Before your agent is live

Before you have deployed for the first time, the Publish page does not show the tabs described above. It shows a single install screen instead: one Copy embed code button, the snippet underneath it for reference, and a Check again control to re-test once you have pasted it. This is deliberate. Before anything is on your site there is only one thing worth doing, so the page shows only that.

Every other setting is still there, behind the Customize appearance and settings row at the bottom: your display name, the welcome message, colours, which model answers, the Install snippet, handover and tools. Opening it swaps the install screen for the full settings, and Back to Deploy returns you to the copy button. Nothing is lost by ignoring it for now.

Which of the two you see depends on the link you followed. The Publish link in your sidebar, and every hand-off from the end of setup, open the install screen, so the copy button is the first thing in front of you. A link that names a settings tab, such as Customize on your dashboard, opens the settings on that tab instead. Either way the other one is a single press away, and the tab you asked for is the one that opens.

You get the tabbed layout as soon as you press Update live agent. You do not have to wait for a visitor: deploying once is enough to switch the page over, whether or not anybody has loaded your site yet. And once your agent really is live, the tabs are simply what the page is.

On a phone or tablet

On a wide screen the Publish page shows your settings on the left and the live widget preview on the right. There is not room for both on a narrow screen, so below roughly 1024px wide the page shows one at a time with a Publish / Preview switcher at the top. It opens on Settings, so Save changes and the action button beside it are on screen straight away, and one tap flips to the preview to check how it looks before you put it on your site.

The settings tabs (Setup, Appearance, Model, Install, Handover, Tools) scroll sideways on a narrow screen, so swipe across them to reach the later ones. Everything you can do on a desktop, including deploying, you can now do from a phone.

Confirm it worked

After you paste the snippet, open your site, look for the chat bubble, and send it a test message. Back on the Deploy page the status line turns green, Live on your site ✓, the moment a page carrying your snippet loads. Press Check again under the copy button (or on the Install tab) to re-check without reloading.

After you update

When an update to a live agent succeeds, a success screen confirms it on the spot: Your AI agent is live. It also hands you the two most useful next steps so you don't have to hunt for them:

• The embed snippet. If your AI agent isn't on your website yet, copy the snippet straight from the success screen and paste it into your site's HTML.
• Preview your agent. Opens a preview of your AI agent in a new tab, here on Dante rather than on your own site, so you can send it a message and see how it will answer. It does not check whether the snippet is on your website yet.

If your plan still shows the "Powered by Dante AI" badge, the success screen closes with one quiet View plans link so you can remove Dante AI branding and see who is converting. It is optional, never blocks the next steps above, and does not appear once you are on Pro or already have the matching add-on active.

The success screen never locks you in. Close it with the X, the Done button, the Escape key, or a click outside the panel, and it quietly dismisses itself after a few seconds if you leave it untouched. Your update is already live either way.

If you deploy before adding knowledge

You can deploy an AI agent that has no knowledge sources yet, and nothing stops you. What changes is what your visitors hear.

An AI agent with no knowledge has nothing of yours to answer from, so rather than guessing, it gives every visitor the same short, honest reply:

This is deliberate. The alternative is an AI agent on your website answering questions about your business from general knowledge, which is how a live agent ends up stating things about your products, pricing, or policies that you never said. We would rather it say nothing than put words in your mouth.

• It never mentions Dante AI. Your visitors see a reply in your voice, with no mention of training, sources, or anything behind the scenes.
• It clears itself. Add a website, upload files, or paste text under Knowledge, and your AI agent starts answering from your content on the very next message. No redeploy needed.
• It can come back. If a scheduled recrawl later fails and leaves your AI agent with nothing to answer from, you will see the same reply again. Your dashboard tells you when this happens, so you do not have to notice it yourself.

In your sandbox you get a different, more useful version of this message with a direct link to add knowledge, because that screen is for you rather than your visitors.

If your live AI agent stops answering

A website can change after you go live. A firewall rule gets tightened, a security layer starts challenging automated visitors, or the pages we were reading move. When that happens, a scheduled recrawl can come back empty and leave a live AI agent with nothing of yours to answer from, even though it was working perfectly the day before.

You do not have to catch that yourself. On your dashboard, an AI agent in this state stops showing the green Live label and shows Live, not answering instead, with a note directly on the card that tells you:

• Which source is the problem, by address, so you are not guessing which one broke.
• What actually happened, in plain language. We could not connect at all, your site's security layer served us a challenge page, we found no readable pages, and so on.
• What to do about it, specific to that cause. Where the fix is allowing our crawler through, the note lists the exact addresses to allow.

We deliberately do not retry the crawl for you. If your site is turning us away, repeatedly knocking on the door does not help, and a fresh crawl uses your plan's character allowance. You decide when to run it again.

The notice clears itself as soon as your AI agent can answer from something again. That can be the original source once it crawls successfully, or a completely different one: uploading a document under Knowledge is often the fastest way back if your site is hard to crawl.

Two embed types

Pick the embed type on the Install tab. The snippet you copy changes with your choice.

• Floating AI agent. A launcher button in the bottom right that opens a chat window. Best for support and sales widgets on a customer-facing site.
• Iframe embed. A drop-in iframe you place anywhere on the page, for a dedicated chat page, a help centre, or an inquiry form. It defaults to full width and 600px tall, and you can change those values in the tag.

Allowed domains

Before you copy the snippet, add the hostnames where you'll embed it. The widget refuses to load anywhere else, which stops someone copying your snippet and running up your usage. The field also suggests hostnames pulled from your training sources so you can lock it in one tap.

• Hostnames only. No https://, no path, no port.
• www and non-www are covered together. Add example.com and we automatically also allow www.example.com (and the other way round), so your widget loads whether visitors land on the bare domain or the www version. You'll see both lines appear and a quick confirmation when this happens.
• Other subdomains count as separate hosts. Add both example.com and app.example.com if you embed on both.
• Leave it blank to allow the widget on any site. Useful during local testing.

Copy and install the snippet

On the Install tab, click Copy embed code. What you copy depends on the embed type you picked:

• Floating AI agent. A single <script> tag that carries your data-agent-id and data-widget-key. Paste it once, just before the closing </body> tag, on every page where you want the launcher.
• Iframe embed. A single <iframe> tag pointing at your agent. Drop it wherever you want the chat to appear.

Copying and pasting the snippet is the deploy. Your AI agent goes live the first time someone loads a page carrying it, and the status line on the Deploy page turns green when that happens. Anything you save inside Dante AI after that reaches your site when you press Update live agent.

Not sure where the code goes? Both publish screens answer that, with the same builder guide. On the Install tab it sits under the snippet. On the first-install screen you get a Where do I paste this? link under the snippet, and it opens by itself the moment you copy. Either way, pick your site builder (WordPress, Wix, Squarespace, Shopify, gamma.site, Vercel, Google Sites, or any HTML site) and you get three exact steps for that builder. Your pick is remembered for next time. There is a longer version of the same guidance in Embedding your agent.

Your widget key

The Install tab shows a widget key that authenticates the embed. Keep it private.

Paid switches on the Publish page

Two switches sit behind a plan gate. Both are included on Advanced and Pro. On Starter, one of them can be added for a monthly fee; toggling a gated switch opens that prompt, and the switch turns on once the payment confirms.

• Dante AI branding. On the Appearance tab. By default the widget shows a small "Powered by Dante AI" badge; turn this switch on to hide it for a fully white-labeled widget. Included on Advanced and Pro. On Starter it is a $50 a month add-on.
• Human handover. On the Handover tab. Lets visitors ask to reach a person, routed to your team inbox. Included on Advanced and Pro. It is not sold separately.

Offer to take contact details

The first switch on the Handover tab is the one for agents that do not have Human handover, and it is on every plan. It decides what a visitor gets when they type something like "can I talk to a human" at an agent with no handover behind it.

• On by default, on every agent, because it is what your agent already did before the switch existed. Left on, a visitor who asks for a person is shown a two-field form asking for their name and email, introduced with "The team is not available right now. Leave your name and email and they will get back to you." Fill it in and they see "Thanks. Your details have been passed to the team." Dismiss it and they carry on chatting with the agent.
• Turned off, that visitor just gets an answer from your agent: no form, no name, no email, and nothing implying that somebody will call them back.
• Where the details go. Straight to Contacts and leads, attached to that conversation, on every plan. This is the one route into that list that does not need lead capture switched on.
• It is a promise in your name, so leave it on only if somebody will read those addresses and reply. If your chat is entirely self-serve, turn it off and your agent answers the question instead.
• Not a sub-setting of Human handover. It applies only while Human handover is off. If you have handover on, your visitors reach your team through the Inbox instead and this switch changes nothing.
• Published widget only. The offer comes from a visitor typing the request on your live site, so it does not appear in the preview beside your settings. Press Update live agent after changing it, like any other setting here.

Let visitors attach files

Once Human handover is enabled, the Handover tab has a Let visitors attach files switch. Turn it on and a paperclip appears in the widget input the moment a human joins the chat, so the visitor can send the screenshot or document that explains their problem instead of describing it.

• Off by default. Visitors cannot upload anything until you turn this on. It is deliberately opt-in: uploads are stored against your workspace, so we never start accepting files on your behalf.
• Only during a live handover. The paperclip appears only while a human has taken the conversation over. It is not available while the AI is answering.
• What visitors can send. Images (PNG, JPG, WebP) up to 5 MB, and PDF, Word (.docx), Excel (.xlsx), CSV or plain-text files up to 10 MB. Anything else is rejected, including the legacy .doc and .xls formats.
• Private storage. Files are stored privately and are only ever shown to your team, through links that expire.
• Kept for 14 days. Attachments are deleted automatically 14 days after the handover is resolved, and immediately if you delete the conversation or the workspace. If you need a file for longer than that, download it from the Inbox while the handover is open.
• Your team is never blocked. Operators can always attach files to their replies from the Inbox, whether or not this switch is on. It controls visitor uploads only.

Email transcripts to your support inbox

Once Human handover is enabled, the Handover tab has an Email conversations to your support team switch. Turn it on and enter an inbox address: when an operator resolves a handover, Dante AI emails the full transcript to that address, with links to any files the visitor or operator attached, so your team can work the ticket without logging into Dante AI.

AI search visibility

On the Install tab you'll find an Allow AI search engines to find this agent toggle. When on, AI assistants and search tools can read a public summary of this agent.

• Off by default. Nothing about your agent is exposed to AI engines until you turn this on. It applies the moment you toggle it, no separate update needed.
• Your agent must be live. The summary only becomes available once your agent has been deployed on a real site. Unpublished agents are never exposed.
• Public-safe only. We share just four things: your agent's public display name, a short description of what it does, a few generic capability lines (for example "Trained on website content"), and the link to chat with it. Your persona or system prompt, your settings, your training URLs, and any private configuration are never included.

Undo an update

Under the status line, once you have pushed an update, you'll find Undo and an Earlier versions menu holding your last 10 updates. Undo puts the previous version straight back on your site. Picking an earlier version loads it into the editor as a draft, so it does not reach your site until you press Update live agent again.

Stuck? We're here.

Every plan, including Free, comes with human support. If something isn't behaving the way you expect after following the steps above, send us a note and we'll get back to you promptly.

Contact our team →