> 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/use-cases/tehpodderzhka.md).

# Technical support

First-line support from the knowledge base, handling negative feedback and escalation

The agent closes standard tickets using the knowledge base, smooths over negative sentiment, and passes the complex case to a human operator with the full conversation history.

Source on the website: [Technical support](https://athenachat.ai/ru/use-cases/tech-support/).

## What it solves

* The queue lasts for hours, and there is no support at night.
* 80% of questions are the same: password, order status, “how does it work?”.
* Requests are scattered across messengers and email; the knowledge base is not used.

## How it works

1. Responds immediately in any [channel](/documentation/documentation-en/channels.md).
2. Looks for the answer in [knowledge base](/documentation/documentation-en/features/knowledge-base.md) and documents — instructions, FAQ, order status.
3. With a dissatisfied customer, speaks calmly and collects contact details for a person.
4. A complex case is handed off to an operator through [trigger](/documentation/documentation-en/features/agent-setup/triggers.md) — the request already contains context.

## What to configure

| In the dashboard                                                                       | Why                                                                          |
| -------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
| [Instructions](/documentation/documentation-en/features/agent-setup/general.md)        | What can be solved independently, when to call in a person                   |
| [Knowledge base](/documentation/documentation-en/features/knowledge-base.md)           | FAQ, instructions, procedures                                                |
| [Triggers](/documentation/documentation-en/features/agent-setup/triggers.md)           | Stop words like “operator,” escalation                                       |
| [Working hours](/documentation/documentation-en/features/agent-setup/working-hours.md) | Auto-reply outside of shift if the agent is not supposed to respond at night |

**Example task:** “Reply according to the FAQ from the knowledge base. If the customer is dissatisfied or the question is not in the knowledge base, pass the conversation to an operator.”

## Examples

**Online school.** Schedules, payments, common technical questions — an administrator without 60% of the routine.

**IT platform.** Multilingual support, complex cases in CRM.


---

# 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/use-cases/tehpodderzhka.md?ask=<question>&goal=<endgoal>
```

`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.