> For the complete documentation index, see [llms.txt](https://docs.athenachat.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.athenachat.ai/readme.md). # Introduction Welcome to the Athena AI docs — an AI agent platform for business Welcome to the **Athena AI** knowledge base — your guide to setting up AI agents, connecting channels, and integrating with your CRM. Whether you're exploring the platform for the first time or already tailoring an agent to your business, start here. [Open your Athena account →](https://app.athenachat.ai) [Athena AI website →](https://athenachat.ai/) *** ## What is Athena AI? **Athena AI** is a platform for building AI agents that talk to your customers in place of a manager: they answer questions, capture leads, book appointments, and hand complex conversations over to a human. All conversations from messengers and your website land in one inbox. AI agents for sales, support, HR, and operations. CRM integrations. **No code.** Agents use modern LLMs and your knowledge base to give accurate, personalized answers — from simple FAQs to multi-step sales and booking flows. ### How it works ``` 1. Connect channels → Telegram, WhatsApp, your website, social media 2. Train your AI agent → role, instructions, knowledge base — in plain language 3. Connect your CRM → Bitrix24, HubSpot 4. Scale → new channels, agents, and scenarios without development ``` **NPI (Natural Prompt Interface)** is Athena's technology: you describe your business and how the agent should behave in plain text, and the platform turns it into ready-to-use instructions. No prompt engineering skills needed. *** ## Common agent roles AI agents built on Athena most often work as: * **Sales agent** — qualifies leads, answers product questions, and takes the customer all the way to a request * **Support agent** — answers FAQs 24/7 and escalates complex cases to a manager * **Admin agent** — books appointments, sends reminders, and collects contact details * **HR agent** — screens candidates and answers questions about the job See detailed examples by industry on the [**Use cases**](/use-cases.md) page. *** ## Where Athena replies **Messengers:** * [Telegram](/channels/messengers/telegram.md) * [WhatsApp](/channels/messengers/whatsapp.md) (Web and Business API) * [Telegram Business](/channels/messengers/telegram/personal-telegram.md) **Social media:** * [Instagram](/channels/social-media/instagram.md) * [Facebook](/channels/social-media/facebook.md) **Website:** * [Chat Widget](/channels/chat-widget.md) — a widget for your website **CRM and services:** * [Bitrix24](/integrations/bitrix24.md), [HubSpot](/integrations/hubspot.md), [Google Calendar](/integrations/google-calendar.md) Step-by-step connection guides are in the [**Channels**](/channels.md) and [**Integrations**](/integrations.md) sections. *** ## Key features | Feature | Description | | ------------------------------------------------------- | ---------------------------------------------------------------- | | **Single inbox** | All conversations from every channel in the **Inbox** section | | **Plain-text setup** | Role, instructions, task — no programming | | [**Knowledge Base**](/features/knowledge-base.md) | PDF, DOC, websites — the agent answers from your materials | | [**Spreadsheets**](/features/spreadsheets.md) | Structured data for product matching and calculations | | [**Broadcasts**](/features/broadcasts.md) | Reminders to customers when the task isn't completed | | [**Google Calendar**](/integrations/google-calendar.md) | Book customers into available slots | | [**Triggers**](/features/agent-settings/triggers.md) | Stop words, handing the conversation to a human or another agent | | [**Multi-agent**](/features/multi-agent.md) | Several agents in one channel, switched by triggers | *** ## How billing works You pay **by the volume of AI messages** — choose a plan with the limit you need. All features (messengers, CRM, calendar, broadcasts) are included in every plan. * **Free:** 100 messages/month — to get to know the platform * Discounts when you pay for 3, 6, or 12 months Details are on the [**Plans**](/pricing/plans.md) page. ### What's the average monthly cost? The cost depends on **the number of conversations**, **the length of your instructions**, and **the size of your knowledge base** — the more complex the scenario, the more context the model processes for each reply. Rough guide: * **Simple cases** (FAQ, collecting contact details) fit into the basic plans * **Complex cases** (multi-step sales, a large knowledge base, integrations) need a plan with a higher message limit --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.athenachat.ai/readme.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.