> 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/reklamacii.md).

# Claims

Complaints, returns, and claims with categorization

The agent accepts the complaint, clarifies the issue, sorts it into categories, and either provides a ready-made solution from the knowledge base or creates a ticket for the manager.

Source on the website: [Claims](https://athenachat.ai/ru/use-cases/reclamations/).

## What it solves

* The customer waits for hours and leaves a negative review.
* Complaints from messaging apps get lost, and different managers keep asking the same thing.
* There are no categories or priorities: delivery, quality, returns are all mixed together.

## How it works

1. Immediately receives the request and collects the data: issue, order number, phone number.
2. Determines the category: delivery, quality, return, other—and sets the priority.
3. Offers a solution from [the knowledge base](/documentation/documentation-en/features/knowledge-base.md): instructions, return period, next steps.
4. An unusual case goes to the manager. A ticket in CRM with history, the team receives [a notification](/documentation/documentation-en/features/agent-setup/triggers.md).

## What to configure

| In the dashboard                                                                         | Why                                        |
| ---------------------------------------------------------------------------------------- | ------------------------------------------ |
| [Role and instructions](/documentation/documentation-en/features/agent-setup/general.md) | Tone for a complaint, what data to collect |
| [Knowledge base](/documentation/documentation-en/features/knowledge-base.md)             | Return policy, standard solutions          |
| [Triggers](/documentation/documentation-en/features/agent-setup/triggers.md)             | Notify in case of a claim or return        |
| [CRM](/documentation/documentation-en/integrations.md)                                   | Ticket and resolution status               |

**Example task:** “Accept the complaint, clarify the order number and the issue, determine the category. For a standard case, provide a solution from the knowledge base. Otherwise, hand it over to the manager.”

## Examples

**Online store.** Complaints about delivery, quality, and returns in [Telegram](/documentation/documentation-en/channels/messengers/telegram.md) and [WhatsApp\*](/documentation/documentation-en/channels/messengers/whatsapp.md) — sorting, and only the complex ones go to people.

**Online school.** Complaints about lesson quality and equipment, notification to the team, status 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/reklamacii.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.