Support chat
Support chat that knows who it is talking to
Your users write to your team from inside your app. You answer beside their plan, billing, roles and flags, replies they miss go out by email, and your own AI agent can answer first.
Who it's for
For teams who talk to their users
Founders doing support
Answer from one small inbox, without another vendor and another copy of your users.
Growing products
See the plan, invoices, roles and flags of the person asking, without switching tabs.
Teams with an AI agent
Let your own agent answer first on a webhook, labelled as AI, and hand over to a person.
What it does
A small inbox with the whole picture
In your app
A ready-made widget in your brand, in English and Danish, or a headless client for your own UI.
Context beside each conversation
Plan and billing with invoices, roles, flags as they evaluate for the user, sessions and activity.
Email fallback
Replies the user hasn't seen are emailed, and their email answer comes back into the conversation.
Your AI agent, labelled
Your code on the message.created webhook answers first, always labelled as AI, and hands over to your team.
Assign, snooze, close
Internal notes, assign to me, snooze and close. Small on purpose: no helpdesk to learn.
Support access in one click
From the user's context, act as them to see the problem, with a reason and a time limit.
One token
Every check reads the same token
When a user signs in, their token carries who they are, their organisation and role, their plan and payment status, and what your flags target. Your API checks it in one guard, offline, and your UI reads the same answers.
Identitywho signed in, and how
sub · amrRolesthe organisation and what it allows
org.roleBillingthe plan and its payment status
billing.planFlagswhat is switched on for this user
flag()In your code
A headless client, or the widget
Live replies arrive as server-sent events and reconnect by themselves. The widget uses the same client, with your project's colours, logo and corners.
import { openChat } from '@anchring/auth/chat';
const chat = openChat({ auth }); // the signed-in user: your team sees their plan, roles and flags
chat.subscribe((e) => show(e.message)); // live replies from your team or your AI agent
const { conversation } = await chat.start('My invoices are missing');
await chat.send(conversation.id, 'It is invoice 4812');
// Or the ready-made widget, in any framework
import '@anchring/auth/chat-widget';
document.querySelector('anchring-chat')!.auth = auth;The plan
Which plans include it
Prices in euros, excluding VAT. Test environments include every feature on every plan.
Free €0
1 chat seat
Startup €29 a month
2 chat seats
More seats €9 a month each
Team €99 a month
5 chat seats
More seats €9 a month each
Scale €299 a month
15 chat seats
More seats €9 a month each
Enterprise from €2,000 a month
Unlimited chat seats
Sovereign from €20,000 a year
Unlimited chat seats
Questions
Before you start
Is it a helpdesk?
No, on purpose. It is a small inbox: conversations, internal notes, assign, snooze and close, with everything the token knows beside them.
Which AI does it use?
Yours. There is no model of ours: your agent is your code on a webhook, with a server key that reads the context and replies. Its messages are always labelled as AI.
Can visitors who aren't signed in write?
Yes, with Lead gen: visitors on your marketing site start a conversation, and it follows them when they sign up.
Talk to your users where they are
Turn chat on in the test environment, add the widget and answer your first conversation.
Free to start. No card needed.
Products
One token, every pillar
Auth
Hosted sign-in, organisations, roles and enterprise SSO.
Organisations
Teams, invites, custom roles and org switching, with the role in the token.
Billing
Plans, checkout, invoices and EU VAT, with the plan in the token.
Feature flags
Targeting and rollouts, evaluated offline from the token.
Support access
Act as a user with a reason, a time limit and an audit trail.
Lead gen
Chat with visitors, and keep them when they sign up.