# Playbooks Playbooks define which steps your AI Agent goes through for specific requests. They are used whenever a conversation should not just be answered, but handled in a targeted way—for example, when information needs to be collected, checked, or passed on to your team. Playbooks are therefore the central tool for structured conversation workflows with your AI phone assistant.
### **What are Playbooks used for?** Playbooks are suitable for requests that require a clear, structured process. #### **Examples of Playbook use cases:** * Systematically collect and confirm appointment requests * Record callback requests with complete contact details * Document support or service requests in a structured way * Categorize and forward invoice or contract questions For each request, you can define a separate workflow in the Playbook that specifies which information should be collected by the AI Agent. ### How do Playbooks work in the AI Agent? A Playbook guides your AI Agent through a conversation step by step. It specifically collects information such as a customer number, a description of the problem, or a preferred contact method. The AI phone assistant repeats the collected information for confirmation and then passes it on in a structured way, for example by email, webhook, or via a summary in the sipgate app. ### Name Playbooks correctly – the title is crucial The name of a Playbook, together with the condition, determines when it is triggered by the AI Agent. Playbooks should therefore be named clearly and unambiguously and should differ distinctly in subject matter. Similar or imprecise titles can cause the phone assistant to select the wrong Playbook and fail to represent the conversation flow correctly. {% hint style="success" %} 💡 Test the naming of your Playbooks intentionally with different wordings and adjust titles if necessary to ensure clear assignment. {% endhint %} ### Define Playbook conditions Make sure the conditions are precise and specific in order to reliably trigger relevant Playbooks. These conditions could include keywords, specific phrases, or specific requests from callers. Check regularly whether the defined conditions are still applying correctly and optimize them if necessary for better AI Agent performance. ## Use tasks in the Playbook in a targeted way A Playbook consists of individual tasks that define which information the AI Agent should collect during the conversation. Tasks can also be created as optional to represent simple **if-then logic** For example: **If certain information is available, then ask an additional question.** In addition, you can mark tasks so that they appear prominently in the summary. This allows you to specifically control which information is especially important for follow-up processing and should be displayed with priority.\ \ Tasks can be used not only to retrieve information, but also to specifically communicate information and instructions to callers in the context of the Playbook. ### Define a closing action When creating Playbooks, you can set the desired closing action as a transfer to any phone number, to a channel, or as a callback. Channels do not require their own routed phone number for this. The analysis dashboard will then show which channel a call was transferred to. Use tasks to obtain callers' consent for the desired closing action. Based on the response, alternative actions can then be defined. For example: "Ask whether a callback is desired. If not, say that this has been noted and hang up." ### Interaction: Playbooks, knowledge base, and customer questions Playbooks define conversation workflows. The [**knowledge base**](/ai-agents/en/behavior/wissensdatenbank.md) and [**customer questions**](/ai-agents/en/behavior/kundenfragen.md) provide the answers, while Playbooks control the AI Agent's structured approach. Together with conversation management, routing, and follow-up processing, this creates a stable, traceable process for your phone system. {% embed url="" %} {% hint style="info" %} **Note:** The term *scenarios* corresponds to today's **Playbooks**. {% endhint %} --- # Agent Instructions: 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: ``` GET https://help.sipgate.de/ai-agents/en/behavior/playbooks.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.