Frequently asked questions about ChatNeuron

Who benefits most:

ChatNeuron is an AI agent and website chat widget platform. It fits teams that need a fast launch without an integrator and answers strictly from their own documents.

• —SMB with inbound from website and messengers
• —HoReCa, education, clinics/salons, retail, real estate, IT/digital
• —Sales and support teams with lots of FAQ and first-line qualification
• —Teams that need RU data handling and clear usage-based pricing

When ChatNeuron may be overkill:

If you only need cold outreach at scale, a ticket helpdesk, or a complex WhatsApp BSP with broadcast to tens of thousands of contacts, look at specialized tools. ChatNeuron is stronger at inbound: widget, company knowledge, qualification and CRM.

Out of the box:

Typical tasks the agent covers without code:

• —Answers about price list, services, terms and FAQ
• —Contact capture and interest qualification
• —Escalation to a live operator by rules
• —Leads into amoCRM, Bitrix24, Telegram alerts
• —Booking via integrations (YClients, calendar, iiko - on any paid plan)

How it learns:

You upload documents, FAQ or point to a website. The agent finds relevant fragments and answers from them. If nothing fits, it does not invent - it says so and offers to connect you.

The dashboard has unanswered questions: add the missing fact and the agent starts answering similar requests.

Quality depends on knowledge completeness: the more precise FAQ, price list and site pages are, the more confident the dialog. Expand the knowledge base from unanswered questions.

AI agents and channels are not limited by the plan — connect as many channels as you need on any plan. Usage is counted in AI tasks shared by all of the company's agents.

No need for two scenarios for website and Telegram: “Copy to another channel” creates the same agent with the same knowledge and rules.

When price list and FAQ change every week, redrawing bot-builder scenarios is usually the failure source. In ChatNeuron you update a document or page and the agent uses current fragments.

For critical flows keep operator escalation and unanswered-question review.

Pros:

• —Widget live in minutes, no flowcharts
• —A trained agent copies to any channel in a minute
• —Fact control via knowledge base
• —Clear pricing: one price per plan by company size, AI task usage visible in the dashboard

What to watch:

• —When the plan's AI tasks run out, the assistant keeps working and extra tasks (4–6 ₽ per AI task) go on the next invoice; at high volume a bigger plan is cheaper
• —Complex internal systems and SLA are easier on Enterprise
• —Omnichannel focuses on the RU stack (Telegram, WhatsApp, VK, CRM), not a global WhatsApp BSP suite

Typical path:

• —Sign up and create an agent
• —Upload FAQ/price list or crawl the site
• —Paste widget code (Tilda, WordPress, Bitrix, HTML and more)
• —Connect Telegram / CRM if needed

If you need help with an industry scenario, book a demo: sales will walk through rollout order.

• —Docs and widget install per platform
• —Free trial in the dashboard
• —Demo call for non-standard rollouts

Typical setup:

• —Widget / messenger → AI agent
• —Capture contact and request context
• —Create a lead or notify amoCRM / Bitrix24 / Telegram
• —Manager continues in the familiar CRM

What it sits next to:

• —Website: HTML widget (Tilda, WordPress, Bitrix and more)
• —Channels: Telegram, WhatsApp, VK
• —CRM: amoCRM, Bitrix24
• —Booking and services: YClients, calendar, iiko - per integrations catalog
• —In-chat payments: YooKassa

Each agent has its own knowledge base and its own channels, which keeps tone and facts from mixing across brands. The number of agents and channels is not limited by the plan: you choose a plan by company headcount, and AI tasks are one shared pool for all agents.

Model:

Plans are Start (9,900 ₽/mo, up to 5 employees, 2,000 AI tasks), Business (29,900 ₽/mo, up to 25 employees, 7,000 AI tasks), Corporate (99,000 ₽/mo, up to 100 employees, 22,000 AI tasks), with a discount for yearly billing. Agents, AI employees and connectors are unlimited; with your own model AI tasks are unlimited.

Trial: 14 days free: all Business features and 300 AI tasks, no card, so you can test the assistant on your data.

Extra AI tasks cost 4–6 ₽ per AI task depending on the plan, billed as used on the next invoice.

What is usually outside the subscription:

Third-party channel costs (for example WhatsApp provider terms) and external integrator services are separate if you hire them. ChatNeuron itself connects without a mandatory integrator.

An AI task is one assistant action: a reply to a customer, a processed email, a created lead or deal, an automation step. Simple actions on the standard model are one task; a complex task on a powerful model (long context, a large document, multi-step analysis) counts as several.

Plans include monthly AI tasks: Start — 2,000 AI tasks; Business — 7,000 AI tasks; Corporate — 22,000 AI tasks. Agents, AI employees and connectors are unlimited - however many assistants work, usage is one pool for the whole company.

If assistants run on your own model (your own LLM or an on-premise setup), AI tasks are not consumed - there is no limit.

What affects usage:

• —Conversation length: every reply takes the conversation history into account, so long conversations use more
• —Knowledge-base context: the more fragments an answer needs, the more it uses
• —Model: the standard model is one task per action, a powerful model counts a complex task as several
• —Your own model does not consume AI tasks

Plan volumes: Start — 2,000 AI tasks; Business — 7,000 AI tasks; Corporate — 22,000 AI tasks. Actual usage by assistant and task is visible in the dashboard.

When 80% of the month's AI tasks are used, the owner and admins get a warning, and a second notice when the volume runs out. Assistants keep working, leads and conversations stay visible and go to connected CRMs.

Extra AI tasks cost 4–6 ₽ per AI task depending on the plan and are billed as used on the next invoice. If you go over every month, a bigger plan is cheaper - its tasks cost less.

On the Start plan you can choose a "leads only" mode instead of working over the plan: once the volume runs out, the assistant stops answering in substance and asks customers for their contact details, at no extra cost. During the trial (14 days free: all Business features and 300 AI tasks, no card) the assistant also collects leads after the tasks run out, until you choose a plan.

The plan's AI task volume is granted for a month. When the next paid period starts the counter resets and you get the full volume again; the unused remainder does not roll over.

There is nothing to buy in advance: tasks beyond the plan are billed as used - 4–6 ₽ per AI task - on the next invoice. If you go over regularly, a bigger plan is cheaper: Start — 2,000 AI tasks; Business — 7,000 AI tasks; Corporate — 22,000 AI tasks.

Your own model does not consume AI tasks - there is no limit for it.

• —Self-serve: widget, knowledge, core integrations, clear plan
• —Enterprise: manager, SLA, custom integrations and limits
• —Not sure - book a demo and we will suggest a path

The knowledge base, dialogs and leads are stored on servers in the Kazan IT Park data center with 6-level protection, each company's data is isolated and dashboard access is role-based. Before launch read the privacy policy and public offer. Enterprise can include extended security and compliance terms on request.