--- sourceDocument: Australia Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/australia/intelligent-experiences Release : - australia ft:locale : - en-US ft:publication_title : - Australia Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Playbook data gathering and processing AI agent # Playbook data gathering and processing AI agent {#ariaid-title1} Release version: Australia Updated September 10, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete. ## Summary of Playbook data gathering and processing AI agent The Playbook data gathering and processing AI agent in ServiceNow Otto for Creator is designed to automate end-to-end playbook execution by consolidating multiple capabilities such as data gathering, processing, and slot-filling. It leverages a variety of retrieval, reasoning, and action-oriented functions to efficiently handle complex workflows involving multiple distinct tasks or single requests. This agent also processes files attached to instance records, providing summaries and extracting actionable information. Show full answer Show less ## Workflow * Breaks input into sub-objectives when multiple tasks are present; keeps input as one task if singular. * Applies appropriate retrieval methods per sub-objective, including record search, structured knowledge lookups, knowledge article searches, and web searches. * Chains retrieval steps if needed, such as locating related records before extracting details. * For document or attachment processing, it retrieves, summarizes, and displays attachments. * Transforms retrieved data using validation, summarization, classification, translation, or extraction as required. * Combines all outputs into one comprehensive response or returns "No results found" if no data is available. ## Configuration and Access * **Third-party access:** Can be enabled to allow external AI agents to use this agent (default is disabled). * **AI specialist access:** When enabled, provides additional configuration options for tool mapping. Disabled by default. * **Long-term memory:** Optionally enables use of all previous user interactions as context for the AI, disabled by default. * These settings are managed in the AI Agent configs table and system properties. ## Tools and Capabilities * Includes scripts, AI Search, Data Retriever for QnA and summarization, Knowledge Articles retriever, Knowledge Graph, TextToResult API crawler. * Can retrieve and summarize attachments from Glide records. * Supports web search for information gathering. ## Security and Roles * Access is limited to users with the **playbookagentuser** role. * Data access roles are not predefined and may be configured as needed. ## Integration and Usage * Administrators can define triggers to automate agent invocation. * Can be configured as an assistant for Virtual Agent or ServiceNow Otto panel through Assistant Designer. * Designed for use within agentic workflows such as Playbook Activity Assist. This AI agent empowers ServiceNow customers to automate complex data gathering and processing tasks within playbooks, improving efficiency and accuracy by integrating multiple data sources and processing techniques. It provides flexibility in configuration and access control to meet enterprise security and operational requirements. This ServiceNow Otto for Creator agent is a assistant that consolidates data gathering, processing, and slot-filling capabilities. It handles end-to-end playbook execution using a broad toolkit of retrieval, reasoning, and action-oriented functions. The agent also helps with tasks related to processing of files attached to instance records. ## Workflow {#wfs-ply-playbook-data-gathering-and-processing-agent-ai-agent__zsmdlwierhjt} 1. Break the input into separate sub-objectives when it contains multiple distinct tasks; leave it as one task if it's already a single request. 2. Run the appropriate retrieval method for each sub-objective (search across records, structured knowledge lookups, knowledge article search, or web search), including chaining steps together when a task requires first finding related records, then pulling specific details from them. 3. For document/attachment requests, retrieve the attachment, generate a summary, and display it once complete. 4. Apply operations like validation, summarization, classification, translation, or extraction when the task calls for transforming already-retrieved data. 5. Merge all outputs into one response, or display "No results found" if the outcome is empty. {#wfs-ply-playbook-data-gathering-and-processing-agent-ai-agent__ol_zlm_z2p_zjc} {#wfs-ply-playbook-data-gathering-and-processing-agent-ai-agent__zsmdlwierhjt__entry__2} | Field | Description | |-|-| | Allow third party to access this AI agent | When enabled, third-party AI agents can use this agent. This value is off (false) by default. This setting is defined in the AI Agent configs \[sn_aia_agent_config\] table on the External discoverable field. | | Allow AI specialists to access this AI agent | When enabled, AI specialists can use this agent. This value is off (false) by default. When set to true, more configuration options for tools become available so that an AI specialist can map inputs and response templates to tool outputs. This setting is defined in the AI Agent configs \[sn_aia_agent_config\] table on the Specialist enabled field. | | Manage long-term memory | When enabled, all previous user interactions are used as context for the LLM. This value is off (false) by default. This setting is defined by the sn_aia.ltm.enable_long_term_memory system property. For more information, see [ServiceNow Otto AI agents reference](https://www.servicenow.com/docs/MUqSU8rHp3ao~q3QEWgHkA "Find more information about user roles, tables, and the different properties that are installed in ServiceNow Otto AI agents."). | | Tools | Scripts : AI Search Data Retriever : Get results for QnA or Summarization task : Knowledge articles retriever tool : Knowledge Graph TextToResult API crawler : Retrieve attachments of a Glide record : Summarize attachments Web search : Use web search | | Allowed user roles The specific user roles that can access this AI agent. | playbook_agent_user | | Data access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take. | Not defined. | | Triggers | Optional. None defined by default. An admin can specify triggers if desired. For more information, see [Add a trigger to an AI agent](https://www.servicenow.com/docs/NXqRJBQV_Vw00FEzklcAJw "In the guided setup for an AI agent, add triggers to run the AI agent automatically when certain conditions are met."). | | Channels | Configure an assistant for Virtual Agent or ServiceNow Otto panel using [Assistant Designer](https://www.servicenow.com/docs/access?context=configure-now-assist-va&version=australia&pubname=australia-conversational-interfaces&ft:locale=en-US). | | Used in agentic workflows | Playbook Activity Assist | [Table 1. Configuration] Learn more about ServiceNow Otto for Creator at [ServiceNow Otto for Creator](https://www.servicenow.com/docs/access?context=now-assist-for-creator-landing&version=australia&pubname=australia-application-development&ft:locale=en-US).