> For the complete documentation index, see [llms.txt](https://vitrina-blogerov.gitbook.io/bloggers-showcase/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://vitrina-blogerov.gitbook.io/bloggers-showcase/product-docs/product-docs-en/admin-panel/bot-management.md).

# Bot management

The Telegram section manages the bot's AI chat, audience, greeting, mailings, channel posts, and access for Telegram administrators.

### Two control areas

{% tabs %}
{% tab title="AI chat" %}
This is where the AI provider, API key, model, and prompt for the Telegram consultant are configured.
{% endtab %}

{% tab title="Audience" %}
Here you can find user statistics, export, cleanup of those who blocked the bot, channel ID, admin IDs, greeting, mailings, and channel posts.
{% endtab %}
{% endtabs %}

### Bot AI consultant

The AI consultant replies to users inside Telegram. It asks clarifying questions and selects bloggers from the database.

Its settings are separate from the AI search on the storefront. This makes it possible to use different prompts: one for quick search on the website, another for dialogue in Telegram.

<div data-with-frame="true"><figure><img src="https://162603775-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FuwCSpQuu1p5soxSClCET%2Fuploads%2FqgKXM0MkRR5ZuZ5WL7xo%2Fai-bot-section.png?alt=media&amp;token=9518fbd8-4c12-4bc1-8c6b-ff317ebe35a3" alt=""><figcaption></figcaption></figure></div>

{% hint style="danger" %}
For the AI consultant, it is also strongly recommended to use `Groq`. Other providers are available in the interface, but have not gone through a full testing cycle in this release.
{% endhint %}

```mermaid
flowchart TD
    A["User writes to the bot"] --> B["Telegram consultant prompt"]
    B --> C["AI provider and model"]
    C --> D["Selecting bloggers from the database"]
    D --> E["Cards and final message"]
```

### Audience

The audience includes users who have launched the Telegram bot. Based on this database, you can view statistics, export data, and send mailings.

<div data-with-frame="true"><figure><img src="https://162603775-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FuwCSpQuu1p5soxSClCET%2Fuploads%2FYjGYhal3TthQwYG3q7SR%2Ftelegram-audience-2.png?alt=media&amp;token=00b920dc-d463-4024-a9c2-30e96dfe9be7" alt=""><figcaption></figcaption></figure></div>

Main indicators:

* active users;
* users who blocked the bot;
* Excel export;
* cleanup of those who blocked.

{% hint style="info" %}
Telegram does not allow the bot to message a person first. The user must launch the bot at least once to enter the audience.
{% endhint %}

### Channel and administrators

To publish posts in the channel, you need `CHANNEL_ID`. The bot must be added to this channel by an administrator.

<div data-with-frame="true"><figure><img src="https://162603775-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FuwCSpQuu1p5soxSClCET%2Fuploads%2FQgTXldTLkX9E5EpyTrzo%2Ftelegram-audience-1.png?alt=media&amp;token=a1a8b5b5-204c-4924-a55f-2070ec67a4d7" alt=""><figcaption></figcaption></figure></div>

Telegram administrators are specified as a comma-separated list of IDs. These are not web admin panel logins, but numeric Telegram user IDs.

{% tabs %}
{% tab title="CHANNEL\_ID" %}
Used to publish posts to a Telegram channel. This is the channel ID itself, not a link to the channel.
{% endtab %}

{% tab title="Admin IDs" %}
Determine who will see the admin menu inside the Telegram bot. Numeric Telegram user IDs are added.
{% endtab %}
{% endtabs %}

### Greeting

Greeting is the first message the user sees after `/start`. It can be configured with text, media, and buttons.

The catalog button usually leads to the Mini App and uses the link for the current language version.

A good greeting should quickly explain:

* who this bot is;
* how to open the catalog;
* that you can write a request in plain text;
* that AI will help select bloggers.

### Final message

The final message is sent after AI selects bloggers. It is convenient to place a button to contact the agency, a link to the catalog, or other target actions in it.

Its task is not just to end the dialog, but to move the user to the next step: contact a manager, submit a request, or open the storefront.

<details>

<summary>Which buttons are supported</summary>

Buttons can use regular external links and special placeholders, for example a link to the Mini App or a prepared request text.

</details>

### Mailings and posts

A mailing is sent to the bot's users. A post in the channel is published in the specified Telegram channel.

{% hint style="warning" %}
Before mass mailing, check the text, media, and button. After sending, the message will already go to Telegram users.
{% endhint %}


---

# 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://vitrina-blogerov.gitbook.io/bloggers-showcase/product-docs/product-docs-en/admin-panel/bot-management.md?ask=<question>&goal=<user_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.