> 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/hr-i-rekruting.md).

# HR and recruiting

Candidate screening, evaluation, and interview scheduling

The agent engages in dialogue with candidates 24/7: tells them about the vacancy, asks questions, filters out unsuitable ones, and gives you a shortlist with an assessment.

Source on the website: [HR and recruiting](https://athenachat.ai/ru/use-cases/recruitment/).

## What it solves

* Hundreds of responses to one vacancy — manual initial screening takes days.
* The best candidates leave while the recruiter is replying.
* The assessment depends on fatigue and the "first impression".

## How it works

1. You connect the [**channel**](/documentation/documentation-en/channels.md), where candidates write: [Telegram](/documentation/documentation-en/channels/messengers/telegram.md), [WhatsApp\*](/documentation/documentation-en/channels/messengers/whatsapp.md), website, CRM.
2. The agent responds immediately, tells them about the vacancy, the company, and the conditions.
3. Asks questions: experience, schedule, salary, skills, motivation.
4. Compares the answers with the requirements and marks who fits.
5. You receive filtered candidates with a brief summary — you can invite them to an interview.

## What to configure

| In the dashboard                                                                         | Why                                                                |
| ---------------------------------------------------------------------------------------- | ------------------------------------------------------------------ |
| [Role and instructions](/documentation/documentation-en/features/agent-setup/general.md) | HR tone, job criteria, what to ask                                 |
| [Agent task](/documentation/documentation-en/features/agent-setup/general.md)            | Collect contact info and understand whether the candidate is a fit |
| [Knowledge base](/documentation/documentation-en/features/knowledge-base.md)             | Job description, conditions, FAQ for applicants                    |
| [Triggers](/documentation/documentation-en/features/agent-setup/triggers.md)             | Notify when the candidate has passed screening or asks for a human |
| [Integrations](/documentation/documentation-en/integrations.md)                          | Pass the card to CRM                                               |

**Example task:** “Answer questions about the vacancy, ask about experience, city, and salary expectations, assess fit, and pass on the contact if the candidate is suitable.”

## Examples

**Mass hiring in retail.** The agent handled hundreds of responses, and HR held final interviews only with the top candidates.

**IT outsourcing.** Questions about the stack in chat, quick contact in [Telegram](/documentation/documentation-en/channels/messengers/telegram.md), in CRM — already screened developers.


---

# 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/hr-i-rekruting.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.