> 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/behavior/playbooks.md). # Playbooks Playbooks define how your AI Agent responds to specific requests 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. In this way, playbooks form the basis for structured and automated conversation flows.
### What are playbooks used for? Playbooks are suitable for requests that require a clear, structured process. **Examples of use for playbooks:** * Record callback requests with full contact details * Document support or service requests in a structured way * Categorize and route invoice or contract questions * Capture appointment requests when no calendar integration is connected {% hint style="warning" %} **Note:** If you have connected a calendar integration, do not create an additional playbook for scheduling appointments. The AI Agent automatically recognizes appointment requests via the calendar integration and can book appointments directly. An additional playbook can cause the request to be assigned incorrectly. {% endhint %} ### 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 captured details and then passes them on. For example, by email, webhook, or as a summary in the sipgate app. {% hint style="info" %} **Note:** Newly created playbooks are initially deactivated. The AI Agent can only use them for suitable requests after they have been activated. Deactivated playbooks are ignored and do not need to be deleted. {% endhint %} ### Give playbooks clear names and descriptions The title and description of a playbook influence when it is selected by the AI Agent. Formulate both clearly, unambiguously, and with clear topical separation. Similar, imprecise, or overly general details can cause the AI Agent to select an unsuitable playbook. {% hint style="success" icon="lightbulb" %} Test the naming of your playbooks deliberately with different formulations and adjust titles if needed to ensure clear assignment. {% endhint %} ### Define playbook conditions Make sure the conditions are precise and specific to reliably trigger relevant playbooks. These conditions could include keywords, certain phrases, or specific callers' concerns. Regularly check whether the defined conditions are still working correctly and optimize them if needed for better AI Agent performance. ## Use tasks in the playbook in a targeted way A playbook consists of individual tasks. They define what the AI Agent should do in the conversation: * **Request information**, for example customer numbers, contact details, or problem descriptions * **Pass on instructions**, such as instructions or information for callers * **Map simple if-then workflows**, for example, ask an additional question depending on an answer * **Highlight important details in the summary**, so they are directly visible for follow-up processing Tasks can be created as mandatory or optional. This allows the conversation flow to be tailored specifically to the respective request. Further information can be found under [**Summaries & Transcripts**.](/ai-agents/en/post-processing/summaries-and-transcripts.md) ### Define closing action When creating playbooks, you can set the desired closing action as a transfer to a freely selectable phone number, to a channel, or a callback. Channels do not require their own routed phone number for this. The analytics dashboard will then show which channel a call was transferred to. Use tasks to obtain the callers' consent for the desired closing action. Based on the answer, alternative actions can then be defined. e.g. “Ask whether a callback is desired. If not, say that this will be noted and hang up.” ### Interaction: Playbooks, knowledge base, and customer questions Playbooks define conversation flows. 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. In combination with conversation handling, routing, and follow-up processing, 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.de/ai-agents/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.