AI support: how to set everything up

Once you register, the cabinet builds your own platform, usually in about a minute: a support admin panel, a chat for your website and an AI assistant. It opens as soon as you confirm your email with the link we send. The bot answers only from your knowledge base, so start there. Everything that rests on your own accounts (domain, mailbox, Telegram bot, website) you connect yourself: we do not ask for access to them. Questions, or something does not work: support@epavdesk.com.

Full product documentation, in English: https://docs.epavdesk.com.

Where to start

What is ready:

• the support admin panel at the address from the cabinet. The login is your email, the password is in the cabinet, block «Panel password». We keep a copy of it, so change it in the panel: «Teammates», «Agents», your own account;
• the AI assistant that answers visitors from the knowledge base;
• the chat for your website and the code to paste into it;
• the team the bot hands conversations to when it cannot answer itself. You are in it.

What to do, in this order:

1. Knowledge base (section 6). Make the first article about your company: what you do, for whom, where and how to reach you. The bot takes answers only from the knowledge base, and it answers «what do you do?» from this article.
2. Chat on your website (section 5).
3. Colleagues who answer when the bot hands a conversation over, and emails to them about handed over conversations (section 7).
4. Language of the panel, the chat and the bot, if you need other than English (section 8).
5. Email and Telegram, if your customers write to you there (sections 2 and 3).
6. Your own support address, if you need one (section 1). If you want your own domain, start with this: DNS records need time.

The model that answers and billing are in sections 9 and 10.

Paths in the panel below are also given as addresses: https://<support address>/admin/... opens the page directly. The panel itself opens with the shield, the last icon of the upper group in the left icon bar (tooltip «Admin»). «Inboxes» in the paths below is the panel item «Channel», «Inboxes» (/admin/inboxes), not the «Inboxes» icon at the top of the bar: that one holds the conversations.

1. Support address

Once your platform opens, the panel and the widget live at an address of ours like vega-07.epavdesk.com. Your company name is deliberately not in it: addresses end up in the public certificate logs, and anyone could read it there. Changing the address is optional, and you do it yourself in the cabinet, the «Support address» block.

Another name under our domain. Type a name, press «Take it». We add the records ourselves, it takes about a minute.

Your own domain, for example support.example.com. Type it, press «Get the records»: the cabinet shows one CNAME and one TXT for verification. Add them wherever you manage the domain's DNS (registrar, Cloudflare, hosting); in Cloudflare both «DNS only» and proxying work. Records propagate from a few minutes to a day. The cabinet checks them itself and switches the address as soon as they appear, so you can close the page: an email will tell you. The check is that https://support.example.com opens the panel login with no certificate warning.

The old address keeps working after the change, so the chat on your site does not break. But the widget code holds the old address: take the new code in the cabinet and replace the old one with it (section 5).

2. Email

This section is for you if customers write to you by email. If they only write in the chat on your site or in Telegram, skip it. The EPAV mailbox does not help here: it only sends emails to your agents (section 7) and does not receive your customers' letters.

What you get:

• letters to your support address (support@example.com) become conversations, the bot and the operators answer them by email from that same address, and the customer's reply lands in the same conversation;
• a visitor who left the site gets the operator's answer by email.

For this you need a mailbox the system reads from (IMAP) and a sending server (SMTP). Use a separate support mailbox, not a personal one: the system reads the whole Inbox and gets full access to the mailbox.

Option A. You have a mailbox with IMAP and SMTP

Google Workspace, Gmail, Zoho, a hosting mailbox and the like.

1. Turn on two-step verification for the mailbox and create an app password (Google: myaccount.google.com/apppasswords, 16 characters). Mail services usually do not accept the normal mailbox password for IMAP and SMTP.
2. Ask your provider for the server addresses. For Gmail and Google Workspace: IMAP imap.gmail.com, port 993, SSL/TLS; SMTP smtp.gmail.com, port 587, STARTTLS.
3. Gmail only: Settings, «Filters and blocked addresses», create a filter «To: support@example.com», «Never send it to spam». The system reads only the Inbox, and a customer letter that Gmail called spam would stay unanswered.
4. Then go to «Entering it into the panel».

Sign-in with Microsoft or Google. Microsoft 365 and Outlook no longer accept a password for IMAP and SMTP: they connect through Microsoft sign-in. Google Workspace and Gmail can connect the same way through Google sign-in, without an app password. You set it up yourself, with an app of your own at Microsoft or Google:

1. Inboxes, «New inbox» (/admin/inboxes/new), «Email», the «Microsoft» or «Google» card. The window shows the callback URL https://<support address>/api/v1/inboxes/oauth/microsoft/callback (for Google, .../google/callback) with a «Copy» button.
2. Register an app in Microsoft Entra or in Google Cloud Console (the window links there), add the callback URL as its redirect URI and give the app access to mail.
3. Enter the app's Client ID and Client secret in the window (Microsoft: also the Tenant ID, if the app is for your organization only), press «Continue» and sign in as the support mailbox.

The inbox is created by itself and named after the address: open it and set «Name», «From email address» and «Scan Interval» as in the table below. For Gmail, the «Never send it to spam» filter described above is needed here too. Which permissions to give the app, step by step: the «Email» article of the documentation, https://docs.epavdesk.com/en/articles/email. If you get stuck, write to support@epavdesk.com, we will set it up together.

Option B. You have no suitable mailbox

A free scheme when the domain's DNS is in Cloudflare: Cloudflare forwards the letters into a separate Gmail, the system picks them up from there and sends through an SMTP service. Customers never see that Gmail: letters go out from support@example.com.

1. Technical Gmail. A new Google account «for personal use», two-step verification, an app password (myaccount.google.com/apppasswords), a filter «To: support@example.com», «Never send it to spam».

2. Cloudflare Email Routing (Compute, Email Service, Email Routing):

   • Destination addresses: add the technical Gmail and confirm it from Cloudflare's letter;
   • Routing rules, Create routing rule: support, Send to an email, the technical Gmail. If a catch-all rule exists, the new one must stand above it;
   • Settings, Subaddressing: turn it on. This is required: the customer's reply goes to support+...@example.com, and without this setting it is lost silently, without even a bounce.
3. An SMTP service for sending, for example SMTP2GO: an account, domain verification (the service gives you DNS records), an SMTP user and password. The SMTP2GO server for Europe is mail-eu.smtp2go.com, port 2525, STARTTLS.

If the domain is not in Cloudflare, forwarding at your registrar or mail provider will do, as long as it supports addresses like support+anything@example.com. Without that, customer replies would be lost.

Entering it into the panel

Email inbox. Inboxes, «New inbox» (/admin/inboxes/new), «Email», «Other provider»:

Continuing a chat by email. Inboxes, «Live chat», the «General» tab, «Conversation continuity email inbox», Email.

Emails to your agents from this same address are set up in section 7, «Emails to your agents».

Check it with three letters

This checks the email inbox above. If all you have is the EPAV mailbox for emails to your agents, there is nothing to check here.

1. From any other mailbox write to support@example.com: in a minute or two a conversation appears in the panel.
2. Answer from the panel: the letter arrives from support@example.com.
3. Reply to it from your mail: the reply lands in the same conversation. If it does not and you are on option B, check Subaddressing in Cloudflare.

Auto-replies («I am on holiday») are skipped by the system, so there will be no loop with an autoresponder.

3. Telegram

1. The bot. In Telegram open @BotFather, /newbot, the bot name, the bot address ending in bot. BotFather sends you a token like 123456789:AAH... - that is the bot's password, do not forward it to anyone. Avatar and description: /setuserpic, /setdescription.
2. Is the bot already running in another system? Turn it off there. One bot, one system: a bot connected in two places at once loses messages. You do not need to remove the old system's webhook by hand: saving the inbox sets ours.
3. The panel. Inboxes, «New inbox» (/admin/inboxes/new), Telegram:

The notice «you are being answered by an AI» is always added to the first message and cannot be removed: the EU AI Act requires it. The greeting and this notice come in the language of the person's Telegram. The form will not save a wrong token: Telegram checks it right away.

Leave «Greeting message» in the «Automatic replies» section empty: with the bot, the first message comes from the «First message» field together with the AI notice. The rest of the form is optional:

• «Away message» goes out when a customer writes outside business hours and an agent is handling the conversation. Pick the business hours and the time zone next to it. While the bot handles the conversation, it is not sent: the bot answers around the clock.
• «CSAT Surveys»: when the conversation is resolved, the customer rates it with stars right in Telegram.
• «Reopen window»: if the customer writes within this many hours after the conversation was resolved, the same conversation continues instead of a new one.

Further down the form has two switches:

• «AI chat without agents»: the bot answers on its own and never hands the conversation to operators. When the knowledge base has no answer, it says so and asks for another question. Turn it on when there are no operators, for example when the bot answers employees from internal documentation.
• «Invite link only»: the bot answers only people who opened it through the link in the form (https://t.me/<bot>?start=<code>). Everyone else gets a note that it works by invitation only, and nothing from them appears in the panel. You need this when the knowledge base is internal: anyone can find a Telegram bot through search. After you save, the link appears in the form with «Copy» and «New link» next to it. A new link switches the old one off: everyone who joined through it opens the new one once (someone left the team or the link leaked). To remove one person: their contact, «Block contact».

Share the link where only your people see it: your team chat or the sidebar of your Confluence space. In Confluence that is Space tools → Configure sidebar → Add link; it needs space administrator rights, not rights over the whole wiki.

4. Check. Write to the bot (with the invite link on, open it through the link): the greeting and an answer arrive.

The bot answers in private messages; it does not read group messages.

Token leaked. @BotFather, /mybots, your bot, API Token, Revoke current token. Paste the new token in the panel: Inboxes, Telegram, «Bot token», Save. The field shows dots in place of the saved token: delete them and paste the new one. Dots left as they are keep the old token, and an empty field is not accepted.

4. The bot on a channel added after launch

Channels that existed at launch are already served by the bot. A channel added later gets the bot through a rule:

Automations (/admin/automations), the «New conversation» tab, «New rule»:

• name: Telegram to assistant (or Email to assistant);
• conditions: «Inbox», equals, your new inbox;
• actions: «Assign agent», your AI assistant (it sits in the list next to the operators);
• save, the rule is on.

Or write to us at support@epavdesk.com: the rule will appear by itself at the next system update.

To take the bot off a channel, switch that rule off. To hand the bot a single conversation an operator was running: the conversation card, «Details», «Actions», assignee, the assistant.

The bot only outside working hours: add to the channel's rule the condition «Business hours», equals, «Closed (outside business hours)». The hours come from the conversation's team, or else from «General»; if there are none anywhere, the condition never matches and the bot takes no conversation.

5. The widget on your site

1. Inboxes (/admin/inboxes), «Live chat», the «Setup» tab, the «Installation» section: copy the code.
2. Your developer pastes it before the closing </body> tag on every page where you want the chat.
3. The same «Setup» tab, the «Security» section, «Domain list»: the addresses of your sites, one per line. *.example.com covers only subdomains, so add example.com separately. An empty list means the widget can be embedded on any site.
4. Visitors who are signed in on your site can enter the chat under their own account: the «Setup» tab, the «Identity verification» section.

If the support address changes, the code on the site has to be updated.

Site builders: where to paste the code

The code works anywhere on the page, at the end of <body> or in <head>. Paste it once into the setting for the whole site, not into a block on one page, then check it in the cabinet: step «Widget on the site», «I pasted it, please check».

• WordPress (your own hosting): install the free plugin «WPCode - Insert Headers and Footers» («Plugins», «Add New Plugin»), then «Code Snippets», «Header & Footer», paste the code into «Footer» and press «Save Changes». On WordPress.com plugins need a paid plan. If the site has a caching plugin, clear its cache. WP Rocket with «Delay JavaScript execution» on shows the chat only after the visitor scrolls or clicks: add widget.js to its «Excluded JavaScript Files».
• Shopify: «Online Store», «Edit theme», in the footer area «Add section», «Custom Liquid», paste the code, «Save». Or «Edit code», the file layout/theme.liquid, before </body>. A theme update or another theme does not carry the code over: paste it again. Checkout pages show no chat.
• Tilda: «Site settings», «Insert Code» (in older versions «More»), «HTML code for the HEAD section», save, then «Publish all pages». Needs a paid plan (Personal or Business): on the free plan custom code is off.
• Wix: «Settings», «Custom Code», «+ Add Custom Code», paste the code, «All pages», «Body - end», «Apply». Needs a Premium plan and a connected domain. If you choose a category other than «Essential» in «Code Type», the chat appears only after the visitor accepts cookies. Do not use the «Embed HTML» element: it shuts the chat into a box on one page.
• Webflow: «Site settings», «Custom code», «Footer code», «Save changes», then «Publish». Needs a paid Site plan or a paid Workspace.

How the chat looks. Inboxes, «Live chat», the «Designer» tab: colors, font, window and button sizes. On top there are two tabs: «Website» is the chat on your site, «App» is the chat in your mobile app, if you connected one. Website changes are stored by the «Save» button of the settings page. In the «Widget type» group you can pick «AI chat»: the chat opens straight into the conversation, without the home screen and the list of conversations, and the «New conversation» button in the header starts over. Who answers, the bot or agents, does not depend on this type: that is the setting below.

AI chat without agents. Inboxes (/admin/inboxes), «Live chat», the «Conversations» tab, the «Features» section, «AI chat without agents», «Save». The bot answers on its own and never hands the conversation to agents. When the knowledge base has no answer, it says so and asks for another question, and the conversation goes on. Office hours are not shown in the chat, and there is no reply limit. The conversations are in the common list, and an agent can answer any of them by assigning it to themselves. If you need both an AI chat and a chat with agents, create a second «Live chat» inbox, turn this switch on there and route it to the assistant with a rule (section 4).

Voice messages. A customer can say the question instead of typing it: in Telegram and WhatsApp as usual, in the chat on your site and in the app with the microphone button next to the paperclip. On the first tap the browser or the phone asks for permission to use the microphone. The bot answers a voice message in text, as if the question were typed, and the agent sees the text under the recording, marked «Voice message transcript». This works once speech recognition is set up (section 9). To remove the microphone button: «Designer», the «Voice messages» switch. In a mobile app the microphone needs one Android permission line, which the app developer adds (see the chat package guide).

6. The knowledge base

The bot answers from the knowledge base and nothing else. You keep it going: «Knowledge base» (/admin/ai/snippets), «Add knowledge» - files (PDF, Markdown, text, HTML) and links, including your site's sitemap.xml. The state of every article is visible in the list: «In search» means the bot answers from it.

A Confluence wiki is connected in the same place, on the «Confluence» tab: the address, the email and an access token, then tick the spaces. From then on the knowledge base picks up new and changed pages once a day and removes deleted ones (right away with «Update now»), and these articles are edited in Confluence. The wiki must open from the internet: Confluence Cloud (an address like acme.atlassian.net) or your own server with a public address. The bot reads Confluence tables row by row with their column names, and when asked for a link it sends the address of the page in Confluence.

The bot answers everyone who sees the chat. If the chat is on an open website, connect only spaces your customers may read. The chat can also live inside Confluence itself, for employees: the code is in the cabinet, step «Widget on the site», tab «In Confluence» (and in the panel: the «Live chat» inbox, the «Setup» tab, the «Installation» section). Paste it into General Configuration → Look and Feel → Custom HTML → At end of the BODY, and only signed-in employees see the chat. Only a Confluence system administrator can paste it, and the chat then appears on every page of the whole wiki, for every team. If the administrator says no (common in large companies), set up a Telegram bot with «Invite link only» switched on (section 3) and put the link in the sidebar of your space: space administrator rights are enough for that.

Make the first article about your company: what you do, for whom, contacts. While our models answer, the assistant description is closed for editing (section 9), and the bot answers general questions about you from this article.

You can delegate this to your own AI (Claude, ChatGPT, Cursor): «AI, Connect your AI» (/admin/ai/mcp), the step by step instructions are there too. Allowing a connection takes a staff member with the «Manage AI features» permission, and any connection is switched off in the same place with one button.

Check the whole knowledge base with your AI. On the same page, block «4. Check the knowledge base», there is a ready request to copy into your AI; in Claude it is also a command, «Check the knowledge base». The AI asks the knowledge base the questions your customers ask, finds what the bot cannot answer, contradictions (different prices or addresses in different articles) and duplicates, and proposes fixes; it writes only after you confirm. When you import pages of your website, questions of collapsible FAQ blocks are kept as headings, and email addresses and phone numbers, the footer included, are collected into one article «Contacts of example.com» per website and language. More: https://docs.epavdesk.com/en/articles/check-your-knowledge-base-with-your-ai

What matters more than volume: search cuts every article at its headings, and the bot gets only the pieces that match the question. So give each question its own section, under a heading that names it, written the way a customer asks it. Clear sections matter more than the number of articles: one long article with good headings works as well as many short ones.

Orders and bookings: ready-made actions

The bot can tell a customer the status of their order in Shopify or WooCommerce, or book an appointment in Cal.com. In the cabinet, card «Ready-made bot actions», enter the keys of your store or calendar and press «Connect»: the cabinet checks them and adds the action to your assistant. Before showing an order or booking, the bot asks the customer to confirm their email with a code, and it shows only orders placed with that email. The code goes from your own mail or from the EPAV mailbox (section «Emails to your agents»): without one of them it cannot be sent. Where to get the keys: https://docs.epavdesk.com/en/articles/ready-made-actions

When the bot hands a conversation to people, you can also send the contact to your CRM through Make, n8n or Zapier: https://docs.epavdesk.com/en/articles/send-handoffs-to-your-crm

7. Agents and handing conversations over

The bot hands a conversation to people when it cannot answer or the visitor asks for a human. The conversation goes to the default team (a new platform has one: «First line»). You are already in it.

How agents learn about a handed over conversation:

• while the conversation is open, it is assigned automatically to a team member who has the panel open, even if they are idle, but not to one who switched on «Away» in their avatar menu or closed the panel more than five minutes ago;
• the whole team gets a notification in the panel and an email «A conversation is waiting for an operator». Emails go out once emails to your agents are set up, with your own mail or the EPAV mailbox (below); without them, only the panel notification remains.

The team email comes from the rule «Handoff to a team → notify the team» in «Automations» (/admin/automations): you can turn it off or change the text.

If you have no agents at all, switch the chat to «AI chat without agents» (section 5): the bot will not promise a human.

«Call me back». When a customer asks to be called, the bot asks for the number and hands the conversation to your agents. A number already known from the app or WhatsApp is not asked again. The conversation gets a note «Asks to be called back: number», with the convenient time if the customer named one, and the customer is told they will get a call back. Call from your own phone: the system has no calls. In the AI chat without agents the bot does not offer a call.

Answering from a phone

The panel works in a phone's browser and can be added to the home screen: open your support address, sign in, then in Chrome on Android the menu and «Add to Home screen» or «Install app», in Safari on iPhone «Share» and «Add to Home Screen». It opens from its own icon with your site's name. In the panel, «Account > Notifications», switch on «Browser notifications»: notices about new conversations, conversations given to you and mentions then come to the phone even when the panel is closed. On iPhone this works only in the panel opened from the Home Screen icon (iOS 16.4 or later). The «New conversation» notice is on by default only for the phone and browser, not by email.

Emails to your agents

The panel emails your agents about conversations handed to them, invites new ones and sends password reset links. These emails can go out in two ways.

The EPAV mailbox, the simplest: in the cabinet (my.epavdesk.com), card «Emails to your agents», «Use the EPAV mailbox». Emails then come from helpdesk@epavdesk.com, nothing to set up in the panel. The mailbox rules:

• it is included in every plan: there is no daily quota and no email packs, and you do not pay for the emails separately;
• it works on a paid subscription. If a payment fails, the mailbox works as usual for two more weeks, and after that emails about conversations stop until the payment goes through; invitations and password resets always go (section 10);
• emails go to your sign-up email and to colleagues' addresses confirmed with a code: enter the address, press «Send a code», your colleague tells you the code, enter it in the cabinet;
• each address has a «receives emails» tick: untick it, and emails to your agents stop going there, your sign-up email included. Cabinet emails about payment and limits still go to your sign-up email if it is confirmed;
• to a customer the mailbox sends only one thing, the verification code before the bot's actions (a short email with the code, in the customer's language); any other email to an unconfirmed address is not sent.

It is switched off in the same place with «Back to my own mail»: the panel then sends emails with the mail from Notifications again.

Your own mail. Notifications (/admin/notification), Email: on, the host, port, user, password and TLS of a sending server (SMTP), the sender address, authentication Login. The SMTP of your mailbox or of an SMTP service will do. If you connected email as in section 2, enter the same details as the SMTP of the email inbox; section 2 also says where to get an app password and the server addresses. Emails start going out as soon as you save.

Colleagues

«Teammates», «Agents» (/admin/teams/agents), «New agent»: name, email, the Agent role, the team. Tick «Send welcome email?», it is unticked by default: your colleague gets a link and sets a password. The email goes out only if emails to your agents are set up (above), and with the EPAV mailbox only to a confirmed address: confirm your colleague's address in the cabinet before you add them in the panel. Section 10 says how many agents your plan includes: on Lite and AI chat it is one, yourself.

No email arrived: confirm the address, and ask your colleague to press «Forgot password?» on the sign-in page. You can also do without email: open the saved agent, enter a password in «Set password» and pass it on to your colleague.

8. Language

A new platform is in English. What to switch to another language:

• Platform language: «General» (/admin/general), «Language». It sets the panel labels and the system messages visitors get. System messages switch at the next system update; if you need it at once, write to us at support@epavdesk.com.
• Chat texts (greeting, button labels): Inboxes, «Live chat». A text in several languages is written as lines ru-RU: Здравствуйте!, en: Hello!, and the visitor sees their own language.
• Bot language: «AI», «Assistants» (/admin/ai/assistants), «Languages». Empty: the bot answers in the customer's language, whatever it is. One language: the bot always answers in it, even when the customer writes in another. Several languages: a preference, the bot still answers in the customer's language, and the list decides only when that language is unclear (a short «ok», a bare number).

9. The model that answers

On the trial our free model answers. After payment the cloud AI of your plan answers first: a fast cloud model that also reads screenshots (a separate model describes the image, and the bot answers from the description). It also searches the knowledge base and transcribes voice messages. How much of it the plan includes depends on the level: Standard, AI or AI+ (section 10). The cabinet shows how much is left for the month in the block «What is included and what you have used» and in the block «Model». The budget refills with every payment and does not carry over. We write to your sign-up email when 80% is used and when it runs out.

The cloud AI runs out before the refill. What happens then, you choose in the cabinet, block «Model»: our free model answers (the default), or there is no free model: your own provider answers, and without one the conversation goes to an agent. AI chat has no agents, so there the free model always answers after the cloud AI. There is no extra charge for AI in any case.

Our free model runs on our own capacity, so we do not promise one hundred percent availability: at peak times an answer takes longer, and now and then we switch it off for updates. When neither the cloud AI nor our model answers, the bot does not go silent: the visitor gets a message that a colleague will answer, and the conversation goes to your agents. The state of the model is shown in the cabinet, block «Model».

Where conversations are processed. The cloud AI of the plan works through OpenRouter (USA): the conversation text is processed by the model host on the condition that it keeps no data, and images are described by an Alibaba model with data collection denied. If that does not suit you, put your own provider first (below) or connect your own model in the office.

While our models answer (the cloud AI of the plan or the free one), the assistant description, instructions and guardrails are closed for editing: they are tuned by measurements, and editing them at random quietly makes answers worse. Name, tone, answer length and languages stay open.

Your own provider (ready presets for OpenAI, DeepSeek, OpenRouter and OVHcloud, or any provider with an OpenAI-compatible API): «AI», «Providers» (/admin/ai/providers). It takes over when our models do not answer, and put first it always answers; then you pay for the model, the cloud budget of the plan is not spent, and the assistant description opens. The backup knowledge base search, for when our search model is unavailable, is set up there too.

When the provider's balance runs out. Providers paid in advance (for example OpenRouter and Novita) stop answering at zero. What happens then, you choose on the provider's row in the «Answer generation» list: the next one in the list answers (usually our free model, this is the default) or the conversation goes straight to a person. Such a row shows «out of money», and so does the «Model» block in the cabinet. After a top-up the provider answers again within 5 minutes.

Speech recognition. A separate model turns voice messages into text. On the trial it is ours, free, with the same note about availability; after payment, the cloud AI of your plan. Your own provider: «AI», «Providers», the «Speech recognition» list, ready options OpenAI and Groq; a provider charges less than a cent per minute of speech. If recognition does not answer, the voice message still arrives: the agent listens to the recording, and the bot asks the customer to type the question.

10. Billing and limits

Plans, prices per month excluding VAT. Every plan has three levels: Standard, AI and AI+. The levels have the same limits and differ in price and in the cloud AI of the plan: how many conversations a day it covers. A conversation is one visitor's chat with the bot, about three bot replies on average: a long back-and-forth uses more, a quick question and answer uses less. How much is used you see as a bar with conversations in the cabinet, block «What is included and what you have used», and in the panel at the top of «AI», «Providers».

The current prices are always in the cabinet and on the website: we may change them for new subscriptions, and those who have paid keep their price.

All plans have the same features and differ only in limits. AI chat differs from Lite in one thing: the website chat works in the «AI chat without agents» mode (section 5). The cabinet switches this mode on by itself when you sign up from the AI chat button on our website or pay for AI chat. You can switch it off in the panel, and the cabinet does not switch it back on.

Until the subscription is paid, the cabinet shows «Trial mode, not paid». The trial lasts 7 days from the day you confirm your email. On day 8 the AI assistant is paused: the chat and the panel work, the bot stays silent. On day 14 the platform is deleted together with its conversations and knowledge base. Reminders come on days 5, 7 and 12, and paying at any point before the deletion brings the bot back at once. At the top of the cabinet you see the plan you picked on the website, or the one you already fit into, and the «Pay» button. Under the usage bars in the block «What is included and what you have used» there is the «Plans» list: you can pay for any of them. To change the payment method or cancel, use «Manage billing and cancel».

Moving to a higher plan or level: the «Switch to ...» button next to the plan in the same list. You can move to a plan no lower than yours and with no less cloud AI: a level up, or a higher plan at the same level or above. The limits and the cloud AI grow right away, what you have already used this month counts, the difference for the rest of the month is charged to the same card at once, and from next month you pay the full price of the new plan. Coming from AI chat, the mode without agents stays on: to let the bot pass conversations to people, switch it off in the panel. There is no button for a lower plan: cancel the subscription in «Manage billing and cancel», and when it ends, pay for the plan you need.

Cancelling. After you cancel, everything keeps working until the end of the paid period, including the cloud AI and the EPAV mailbox. The next day the AI assistant is paused: the chat and the panel work, the bot stays silent. After 30 more days the platform is deleted together with its conversations, contacts and knowledge base. The cabinet shows these dates next to the plan, and emails come when you cancel, a week before the end and on the day of the pause. If you need the knowledge base or the contacts, write to support@epavdesk.com before the deletion date and we export them. Paying again at any point before the deletion brings the bot back at once.

Deleting your account. At the bottom of the cabinet, «Delete my account and data» sends us a request: we cancel the subscription and delete the account and the platform within 7 days, the cabinet shows the date.

Invoices and VAT. Card payments go through creem, which acts as the seller for EPAV: its name is on your bank statement and on the invoice, and it charges and pays the VAT. An invoice is made for every payment; creem emails a link to its portal after each payment, and «Manage billing and cancel» opens the same portal. Prices exclude VAT, creem adds it by your location; an EU company that enters a valid VAT number at checkout may get the reverse charge. You can pay with a card, Apple Pay or Google Pay, depending on your country and device. Questions about a payment, a refund or an invoice: support@epavdesk.com.

Paying by bank transfer. If your company needs an invoice to pay by bank transfer, write to support@epavdesk.com with the plan and your company details. Once the money arrives, we switch the plan on until a date, and the cabinet shows «Paid by bank transfer until ...» instead of the payment buttons. A week before that date we contact you about the next invoice. If no new payment arrives, the cancelling rules above apply from the day after that date.

Over a limit, nothing is switched off or cut down. On Lite, Basic and AI chat you cannot buy extra: under the bar the cabinet shows the plan you fit into, with a button to switch. On Ultra you buy extra: we bill the overage for the next month, 10 € per 10 agents, 5 € per thousand knowledge base pieces (about 300 articles), 1 € per gigabyte of storage over the limit, excluding VAT.

Emails about limits go to your sign-up email while the subscription is paid and the email is confirmed. For the knowledge base and storage we write early, once 80% is used; for agents, once there are more of them than the plan includes. Over a limit, on Ultra we write about the invoice, on the other plans we name the plan to move to.

A payment did not go through. The platform keeps working. The cabinet shows «The payment did not go through» and a banner with the «Manage billing» button, where you update the card, and your confirmed sign-up email gets reminders. The EPAV mailbox keeps sending emails to your agents as usual for two more weeks, and the banner shows the last day. After that, emails about conversations through the mailbox stop until the payment goes through, while invitations and password resets still go. With your own mail nothing stops. Once the payment goes through, everything works again at once. If the payment provider gives up retrying, the subscription is cancelled, and the cancelling rules above apply.

WhatsApp messages are billed by Meta, not by us. Since 1 October 2026 Meta charges for every reply in the 24-hour window, by the assistant or by an agent, per message at the rate of the recipient's country. Meta bills you directly in its Billing Hub, where the payment method is added. Current rates are in Meta's pricing documentation. If Meta does not deliver a reply, the message gets a red mark with the reason in your panel language. When the reason is the payment method, the conversation gets a private note and the administrators get one notification a day: no reply arrives until a payment method is in Billing Hub, then send the failed replies again by hand.