A builder for AI bots and automations
Answer customers around the clock — with a bot that knows your documents
Build it with the mouse in an evening, with no developer, and put it on your site, in Telegram, or behind a link. Free once your address is confirmed, no card.
- Execute + Data
- Data
- LLM
- Execute + Data + Streaming
Three steps to a working bot
Describe it in words
The built-in assistant assembles the graph from your description — or take a ready template and change the text. You do not need to understand the machinery at this step.
Try it in the chat
The Test tab is a real run: you see which step is working, what it received, what it returned and what it cost.
Switch on a channel
A chat link, a widget on your site, a Telegram bot, a call from your own system, or a schedule. Same bot, different doors.
Nodes
Drag onto the canvas
| Section | What is inside |
|---|---|
| Input / Output | Entry, Exit |
| AI | AI Agent, LLM, Memory, Document search |
| Logic | If / Else, Switch, Loop |
| Data | Template, Variable, Tables, Database |
| Integrations | HTTP, Email, Telegram, Calendar |
Chat
- 1Palette: drag the step you need onto the canvas.
- 2Canvas: the cards and the links between them are your bot.
- 3Three tabs: build, test, publish.
- 4Assistant: describe the task in words and it builds the graph.
What people build
Every example is a working graph: open it in the editor in one click and adjust it to your case.
A support bot that answers from your documents
Answers customers from your policies and price list, and does not invent what it could not find. The basis of a first-line bot.
The site went down, so a message lands in Telegram
Checks every half hour whether the site answers, and writes to you in Telegram only when it has gone quiet.
A form request, parsed and filed
The form on your site posts a request: the scenario breaks it into fields, writes a row to a table and answers the form straight away.
A photo of a receipt becomes a line of spending
Photograph the receipt, send it to the bot: the amount, the category and the place are already in a table.
The customer taps instead of typing
A menu of buttons instead of a conversation: a tap re-enters the same scenario and takes the right branch.
A request routes itself to the right team
The message is read and sent where it will be answered: sales, support or accounts.
Where it goes
One bot, six doors to it — pick any of them, or all at once.
Chat page
A link you can send a customer. No markup, no hosting.
Site widget
One tag on your page. Your colours, and it will not break your styles.
Telegram bot
Direct chats and groups: attachments, buttons, moderation.
VK bot
Community messages and chats: attachments, buttons, history.
A call from your system
A form, a CRM or your own backend starts the bot over HTTP.
On a schedule
A nightly report or a mailbox check — with nobody in a chat.
And it plugs into what you already run
Credentials live in your workspace and the steps refer to them — keys are never kept inside the bot.
- Telegram
- VK
- amoCRM
- Bitrix24
- Calendars (CalDAV)
- Email (IMAP/SMTP)
- WebDAV
- Any HTTP service
- MCP
128
What it is built from
ready-made steps: model answers, document search, branching, tables, email, calendar, CRM. Four of them are enough for a first bot.
Open the reference →Why you can trust it with customers
Edits do not break the live bot
A saved version is what gets published. You can repair the graph while the previous one keeps answering people.
Mistakes surface before the run
Publishing runs the same check as a run does: a graph that cannot execute never reaches your customers.
Every step is visible
The run history shows what arrived at a step, what it returned, and how many tokens and quarks it spent.
Data stays in your workspace
Files, documents and conversations belong to the workspace rather than to a scenario, and secrets are stored encrypted.
Your own keys, no markup
Connect your own model key and its tokens are not billed here — you already pay for them.
The customer need not be named
A phone number, an address or a name in the question is replaced by a label before the model sees it, and restored in the answer.
What it costs
Free forever
300 quarks a month once your address is confirmed, no card needed. An email arrives when a fifth of them is left.
One answer costs half a quark and up
The run, the model call, and tokens at that model's rate. The first run on your own documents shows the exact price.
Not billed at all
Drafts and edits to the graph, and model tokens on your own provider keys.
Frequently asked
Do I need to write code?
No. A scenario is assembled with the mouse from nodes, and the logic lives in their settings and in templates like {{ inputs.message }}. There is a JavaScript node, but it is rarely needed and never on day one.
Can I use my own model keys?
Yes. Add any OpenAI-compatible endpoint in the workspace settings and its models appear in the dropdowns next to the platform ones. Their tokens are not billed here — you already pay the provider.
Where does the data live?
In your workspace: files, document collections and knowledge bases are scoped to it, each with its own quota. Secrets are stored encrypted and injected into templates as {{ secret.NAME }}.
How do I ship a bot to users?
From the Deploy tab: a public chat link, an embeddable widget behind one script tag, a Telegram bot, a webhook for another system, or a schedule. Same graph version, different channels.
How long does it take to launch, and do I need to hire someone?
A first bot answering behind a link takes about ten minutes: take a template or describe the task to the built-in assistant, pick a model, write what the bot talks about, and switch on a channel. No contractor needed — the docs carry a step-by-step tutorial and a walkthrough of the places people usually get stuck.
What does it cost?
Money buys the plan; inside, the work is counted in quarks, and the plan grants a month's worth of them. One answer costs upwards of half a quark — the run, the model call, and tokens at that model's rate. The first run shows the exact price, because it depends on the model and on how much found text travels into it with the question. Drafts and edits are not billed at all.
What happens when the free quarks run out?
The free plan does not allow going over the balance: new runs start being rejected and a published bot stops answering until the next monthly grant. What is left is always in the wallet at the bottom of the sidebar, and you get an email at 20 per cent left and a second one when the quarks are gone.
Are my conversations and documents used to train models?
The platform trains no models. For sensitive data there are two tools: masking, which replaces phone numbers, addresses and names with labels before the model sees them and restores them in the answer, and running on a key of your own, where the terms are yours.
What if the bot answers a customer incorrectly?
Its behaviour is set by the instruction text, and editing that does not touch the live bot until you publish a new version. Every conversation is kept: you can see what the customer asked, what the bot found in your documents and what it replied — that trail is what you fix the instruction from. If it should not answer on its own when it found nothing, the instruction says so.
What happens when a step fails — say an external service does not respond?
A step can expose its own error output and send the failure down a separate branch, so the bot says something sensible instead of going quiet. With no such branch the run is marked unsuccessful, and the history shows which step failed, on what input, with what error.
Can an external agent drive the platform?
Yes. Assistant MCP exposes a workspace over the MCP protocol: an external agent reads and edits scenarios, runs them and reads the logs. The key is per workspace and read-only by default.
Build your first bot today
Free once your address is confirmed, no card. The first bot is behind a link in about ten minutes — and if something does not go to plan, the docs walk through every place it can break.