> For the complete documentation index, see [llms.txt](https://help.sipgate.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.sipgate.com/documentation/en/behavior/playbooks.md). # Playbooks Playbooks define how your AI Agent responds to specific concerns and which steps are carried out. They are used when conversations should not only be answered, but handled in a targeted way — for example, to collect information, review requests, or pass content on to your team. This makes playbooks the foundation for structured and automated conversation workflows.
### **What are playbooks used for?** Playbooks are suitable for requests that require a clear, structured process. #### **Examples of use cases for playbooks:** * 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 the AI Agent should ask for. ### How do playbooks work? A playbook controls how your AI Agent handles a conversation. It can be used to specifically request information such as customer numbers, problem descriptions, or contact options. The agent confirms the information collected and then forwards it. For example, by email, webhook, or as a summary in the sipgate app. ### Name playbooks correctly The title of a playbook affects when it is selected by the AI Agent. Therefore, use clear and unambiguous names that are thematically distinct from one another. Similar or vague names can cause the agent to select an unsuitable playbook. {% hint style="success" %} 💡 Test the naming of your playbooks deliberately with different phrasings and adjust titles if necessary to ensure clear assignment. {% endhint %} ### Define playbook conditions Make sure the conditions are precise and specific so that relevant playbooks are triggered reliably. These conditions could include keywords, specific phrases, or specific concerns from callers. Regularly check whether the defined conditions are still working 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 map simple **if-then logics** For example: **If a certain piece of 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 convey information and instructions to callers in a targeted way within the context of the playbook. ### Define closing action When creating playbooks, you can set the desired closing action as a transfer to any phone number, to a channel, or a callback. Channels do not require their own routed phone number for this. The analysis dashboard will then show which channel a call was forwarded to. Use tasks to obtain the caller’s 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**](/documentation/en/behavior/wissensdatenbank.md) and [**customer questions**](/documentation/en/behavior/kundenfragen.md) provide the answers, while playbooks control the AI Agent's structured approach. Together with conversation management, routing, and follow-up, this creates a stable, traceable process for your telephony. --- # 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.com/documentation/en/behavior/playbooks.md?ask=&goal= ``` `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.