--- sourceDocument: Brazil Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences Release : - brazil ft:locale : - en-US ft:publication_title : - Brazil Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Procurement product recommendation AI agent # Procurement product recommendation AI agent {#ariaid-title1} Release version: Brazil 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 Procurement product recommendation AI agent The Procurement product recommendation AI agent streamlines sourcing and procurement operations by browsing catalogs, matching user requirements with available products, and creating purchase requests. It processes uploaded quote or Statement of Work (SOW) documents to extract line items and pricing, then guides users through product selection and routing based on vendor status and purchase thresholds. Show full answer Show less ## Key Features * **Product Matching and Recommendations:** Automatically matches requested products to catalog items and presents selectable options for each product. * **Document Processing:** Extracts details from uploaded quotes or SOW files to create purchase requests. * **Routing and Workflow Automation:** Uses a channel decision tool to determine whether requests route to purchasing or sourcing, based on product IDs and other criteria. * **User Interaction:** Presents an interactive HTML plan, prompts users to provide missing information, allows editing, and manages attachments before final submission. * **Configuration Options:** Controls for third-party AI agent access, AI specialist access with enhanced configuration capabilities, and management of long-term memory for context retention. * **Tools and Conversational Topics:** Includes tools for handling attachments, document tasks, recommendation display, and creation of purchasing or sourcing records. * **Access Control:** Restricts usage to specific user roles and data access roles to ensure appropriate permissions. * **Integration and Channels:** Can be configured for Virtual Agent or ServiceNow Otto panel assistants and integrated into agentic workflows for sourcing and procurement. ## Practical Benefits for ServiceNow Customers * Speeds up procurement by automating product recommendations and purchase request creation from quotes or SOW documents. * Enhances accuracy by extracting detailed pricing and line items directly from uploaded documents. * Improves user experience with interactive guidance, error checking, and editable purchase plans. * Supports flexible routing to purchasing or sourcing depending on product and vendor criteria, optimizing workflow efficiency. * Offers configurable access controls and specialist modes to tailor the agent's capabilities to organizational needs. * Integrates seamlessly with existing ServiceNow assistants and workflows, enabling a unified procurement process. This Sourcing and Procurement Operations agent can browse the catalog and create orders. The agent matches user requirements against available items, then routes to submission forms based on vendor status and dollar thresholds. Accepts and processes uploaded quote documents or SOW (Statement of Work) files to extract line items and pricing. ## Workflow {#spo-procurement-product-recommendation-ai-agent__zsmdlwierhjt} 1. Create a purchase request from the quote or statement of work was uploaded by the user. 2. Run recommendations for all requested products, then present them one product at a time as selectable options. Collect a selection or skip for each product before moving on. 3. Assemble the selected products with any available details and run the channel decision tool, which determines whether the request routes to purchasing or sourcing. Render an HTML plan for the user. 4. If the plan flags missing fields, ask the user to provide them, re-run the plan tool, and repeat until nothing is missing. 5. Present the plan and ask the user to submit or edit. Edits are applied by re-running the plan tool with the updates, then re-presenting the plan. 6. Ask about attachments, then submit via either the purchasing or sourcing tool based on whether the selected products have product IDs. {#spo-procurement-product-recommendation-ai-agent__ol_ggm_fgy_zjc} {#spo-procurement-product-recommendation-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/sa1bdHN6FqAGJmyqCFbo6w "Find more information about user roles, tables, and the different properties that are installed in ServiceNow Otto AI agents."). | | Tools | Conversational topics : Add or update attachment : Quote or sow attachment Script : Channel decision and plan creation : Create a document task : Create purchasing record : Create sourcing record : Created record from document : Document type extractor : Recommendation : Show more results | | Allowed user roles The specific user roles that can access this AI agent. | sn_spend_gen_ai.now_assist_requester | | Data access roles The specific user identity roles that determine which data the AI agent can access and what actions it can take. | sn_spend_gen_ai.now_assist_requester, sn_shop.shopper | | 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/TTPcY_6jqFaCPLWj8oH1fQ "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=brazil&pubname=brazil-conversational-interfaces&ft:locale=en-US). | | Used in agentic workflows | Conversational intake for sourcing and procurement | [Table 1. Configuration] Learn more about Sourcing and Procurement Operations at [Sourcing and Procurement Operations](https://www.servicenow.com/docs/access?context=psm-overview&version=brazil&pubname=brazil-source-to-pay-operations&ft:locale=en-US).