> For the complete documentation index, see [llms.txt](https://help.sipgate.de/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.sipgate.de/ai-agents/en/use-cases/first-level-support.md).

# First-level support

The first-level support use case is suitable when incoming support requests should be reliably accepted, pre-sorted, and partially answered directly. The agent handles recurring issues, answers standard questions immediately, and forwards more complex cases in a structured way, without queues.

### What exactly does the agent handle?

In first-level support, the agent answers calls and clarifies the issue. He answers common questions, such as about opening hours, prices, or availability, immediately. For more complex topics, he captures all relevant information and prioritizes the issue for forwarding. This ensures urgent cases reach the right contact person faster. After each conversation, the content is automatically summarized and provided.

### **Briefly explained: How to set up the use case**

{% stepper %}
{% step %}
**Create agent & refine profile**

Create an agent and define in the **company profile** (configuration section) which topics your support covers (e.g. "We help with IT problems and billing questions"). *Tip:* Use the greeting to let callers know that they are speaking with a digital assistant (e.g. "I will take down your ticket or answer quick questions").
{% endstep %}

{% step %}
**Create playbooks for tickets & escalation**

Under playbooks, create guides for problems that a person must solve.

* **Playbook "Incident report":**
  * Condition: "Caller reports a technical problem"
  * Task: "Record error description"
  * Task: "Ask for customer number & urgency"
  * Closing action: Forwarding (to 2nd-level support in emergencies) or announce a callback (standard ticket).
    {% endstep %}

{% step %}
**Store knowledge**

So that the agent can solve standard questions ("How do I reset my password?") immediately without disturbing the team:

* **Knowledge base:** Upload manuals, FAQs, or guides as PDFs.
* **Customer questions:** Store short answers for quick fixes (e.g. "Where can I find my customer number?").
  {% endstep %}

{% step %}
**Ticket creation & notification**

Make sure the call becomes a ticket.

* **Email summary:** Enter the address of your ticket system under *Configuration > Recipients* (many systems automatically convert emails into tickets).
* **Webhooks (recommended):** Use webhooks to push the incident report in a structured way directly into tools like Jira, Zendesk, or Freshdesk.
  {% endstep %}

{% step %}
**Assign phone number**

During the test phase, you will receive free phone numbers from us for testing. However, so that your agent can still be reached after the trial period, you must assign it a phone number.
{% endstep %}
{% endstepper %}

### Benefits at a glance

The agent ensures that calls are answered at all times and no request is lost. Support teams are relieved because routine inquiries are handled automatically and only relevant cases are forwarded. At the same time, conversations remain traceable, as all inquiries are documented and can be evaluated. Statistics and call logs make it possible to see which topics occur particularly often.

<br>


---

# 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://help.sipgate.de/ai-agents/en/use-cases/first-level-support.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.