> 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/documentation/documentation-en/features/agent-setup/general.md). # General Name, language, role, instructions, task, tables, and knowledge bases Tab **General** — who the agent is, how it responds, and what to do when the task is completed. ## How to open **Channels → channel → Edit → General** ![](https://4126380821-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwirYrs8odJMFan3KqfzY%2Fuploads%2F0QVM7ZiEC4QpOPJdE9y2%2Fagent-osnovnye-01.png?alt=media) ## AI agent name Agent name in the dashboard. This is how you distinguish channels and bots from each other. This field does not affect how the agent introduces itself to the client — the client-facing name is set in **the role**. Example in the dashboard: `New Bot`. ## Athena AI language In which language the agent carries on the conversation. Option **All languages** — customers write in different languages, and the agent replies in the customer's language. ## AI agent response delay Pause in seconds before responding. `0` — responds immediately. If you want the reply to look more natural, set a small delay. ## Channel auto-reply Checkbox **Reply to messages even if an auto-reply is present**. If the channel already has its own auto-reply, the agent may stay silent by default. Turn on the checkbox — then Athena will reply anyway. ## AI agent role Who the agent presents itself as to the client — as a new company employee. Write in the second person. > Your name is Marina, you are an employee of the choreography studio "Flexible Path" > You are a sales manager at the Pelican furniture factory. You sell children's chairs. ## Behavior instructions Communication algorithm: tone, constraints, what to clarify, and what actions to trigger. The editor supports headings, lists, links, tables, and code. Switching **Visual / Markdown** — at the bottom right of the field. {% hint style="info" %} The more specific the steps, the more stable the dialog. One instruction — one situation. It is better to separate multiple scenarios with headings inside the field. {% endhint %} ## AI agent task The goal of the conversation in one phrase. When the agent considers the task completed, the block below is triggered. Example: `Enroll a child in classes.` ![](https://4126380821-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwirYrs8odJMFan3KqfzY%2Fuploads%2FRMo5W4I5R0dROiawhPjb%2Fagent-osnovnye-02.png?alt=media) ## Connected tables Button **+ Connect table** gives the agent prices, inventory, or slots from [**Tables**](/documentation/documentation-en/features/tables.md). Without a table, the agent relies only on the role, instructions, and knowledge base. ## Action when task is completed Will be triggered when the AI agent task is completed. | Setting | What it does | | -------------------- | ----------------------------------------------------------------------- | | **End conversation** | The dialog is closed, the agent no longer responds in this conversation | | **Notify** | You receive a conversation summary | **Notification method:** * **Notify by email** * **Notify in** [**Telegram**](/documentation/documentation-en/channels/messengers/telegram.md) In the field **Describe what you want to see in the conversation summary** write what data is needed in the email or message: contact details, selected service, district, conversation outcome. ## Pause and auto-start Two toggles at the bottom of the tab: **Automatically pause the AI agent when human intervention in the conversation is detected.** If an employee writes to the client themselves, the agent stops and does not interrupt. **Set up automatic startup of Athena AI after a specified period of time after it is turned off.** After the pause, the agent will turn back on automatically after the specified time. ## Customer data Block **Choose what information to provide to Athena AI**. Check what the agent can use in responses: * **Client name** * **Client city** * **Phone number** * **Client nickname** ## Message history Toggle **Message history**. If enabled, the agent sees previous messages in the conversation and does not ask the same thing again. ## Knowledge bases In the block [**Knowledge bases**](/documentation/documentation-en/features/knowledge-base.md) choose a ready-made [**knowledge base**](/documentation/documentation-en/features/knowledge-base.md) or leave **Not connected**, if the agent has enough role, instructions, and tables. --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.athenachat.ai/documentation/documentation-en/features/agent-setup/general.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.