> For the complete documentation index, see [llms.txt](https://docs.pascom.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.pascom.net/en/setup/acd/welcome-agent-setup.md). # Setting Up the Welcome Agent Learn how to set up, configure, and test the Welcome Agent of the PASCOM Cloud PBX. The PASCOM Cloud PBX Welcome Agent allows you to intelligently and individually greet callers before they are forwarded. By configuring prompts and reacting to labels, you can personalize the caller experience. For example, you can play special announcements for VIP customers. ### Adding and Configuring the Welcome Agent The basic setup is similar to creating other AI Agents. For more details, refer to the [AI Agents Overview](/en/setup/acd/ai-agents-setup.md). After you click **Add** for the Welcome Agent, configure the basic data: 1. Enter a unique name for your agent under **Label**, such as "Welcome Agent". 2. Optionally, set a suitable **Avatar image**. 3. Define the exact behavior in the **AI Agent description** (Prompt). Here you formulate the instructions for the agent, for example: *"You answer incoming calls as an agent in the office queue at Company XY. Greet the caller depending on the time of day and with salutation and last name. Politely inform the caller that the next available employee will take the call as soon as possible."* 4. Select the desired voice output under **Voice** (e.g., "Voice 1"). 5. Click Save. ![Configure Welcome Agent](https://2713225-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FVIw0BpSv358R2Pr2HflD%2Fuploads%2Fgit-blob-aed52ea39484f0a37fa7ecaf5fdb16da96b59064%2Fwelcome-agent-setup.en.png?alt=media) ### Personalization with Labels A special advantage of the AI Agent is the ability to react to **Labels**. This allows you to implement great individualizations that noticeably improve the caller experience. For example, extend your prompt with the following instruction: *"If the label VIP = yes is set, say that the caller, as a premium customer, can look forward to particularly short waiting times."* The agent evaluates the label accordingly and dynamically adjusts the greeting for this special target group. For more detailed information, refer to the [Labels Guide](/en/setup/acd/labels.md). ### Testing the Welcome Agent in the Simulator Before you deploy your new Welcome Agent live, you can test its behavior safely and extensively. The practical **Call Simulator** is available for this purpose. 1. Click **Simulate** in the top right corner of the agent's basic data. 2. Select a **Caller name** in the simulator, or search for a specific contact via **Select contact**. 3. Enter a **Phone number** for the test call. 4. If necessary, add different labels (e.g., `VIP=yes`) via **Add temporary label** to play back the specific reactions of your agent to this configuration. 5. Click **Simulate** to start the simulation. ![Welcome Agent Simulator](https://2713225-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FVIw0BpSv358R2Pr2HflD%2Fuploads%2Fgit-blob-13cc42e43a0cfb8165b574b07a742595da806903%2Fwelcome-agent-simulator.en.png?alt=media) ### Welcome Agent Deployment Once setup and testing are complete, you can integrate the AI Agent into your phone system. The deployment options are very diverse: you can place the Welcome Agent in call distributions, teams, at users, or in IVR menus. For more details on call distributions, refer to the documentation on [Action Conditions](/en/setup/acd/actions.md). --- # 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 following URL with the `ask` and `goal` query parameters: ``` GET https://docs.pascom.net/en/setup/acd/welcome-agent-setup.md?ask=&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 `build a script that syncs our docs to a CMS` 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.