--- sourceDocument: Australia Enable AI sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/pt-BR/intelligent-experiences Release : - australia ft:locale : - pt-BR ft:publication_title : - Australia Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Classify documents # Classify documents using the Document Intelligence workspace {#ariaid-title1} * Versão de lançamento: Australia * * Atualizado 12 de mar. de 2026 * * ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 min. de leitura Use the Document Intelligence workspace to label your documents. The workspace enables you to train the AI model by providing direct input and by validating or correcting the recommendations provided by DocIntel. Importante: Starting with the Zurich release, Document Intelligence is being prepared for future deprecation. It will be hidden and no longer activated on new instances but will continue to be supported. For details, see the Deprecation Process article \[[KB0867184](https://support.servicenow.com/kb?id=kb_article_view&sysparm_article=KB0867184)\] in the Now Support Knowledge Base. Instead, you can extract information from documents using the Now Assist in Document Intelligence application. For more information, see [Now Assist in Document Intelligence](https://servicenow-prod.fluidtopics.net/Dq_6c8JJ_cu9yJcvDkosRA "Use ServiceNow Now Assist in Document Intelligence to analyze and extract information from unstructured documents with generative AI.With ServiceNow Now Assist in Document Intelligence, you can use generative AI to get key information from digital documents into your automation workflows."). ## Overview of the Document Intelligence workspace {#use-the-docintel-workspace-to-classify__section_cqb_s1l_rxb} The Document Intelligence (DocIntel) workspace provides features that enable you to quickly apply classes or categories to the attached documents and each of their pages. To get started with the Document Intelligence workspace, complete the following: * [Create a document task](https://servicenow-prod.fluidtopics.net/BM_U4YkZNMAg1IPEaRi3~w "Create a document task and upload single or multi-page documents that are in JPEG, PNG, or PDF formats to start extracting text or classifying documents.") for a document classification use case, upload a document, and process the task. * After DocIntel has processed the task, you can begin using the workspace. See [Complete a document task](https://servicenow-prod.fluidtopics.net/okxnD0cZH_cZMWnk4RqQaQ "After the document task processing is finished, complete the task by providing input or review to train the AI."). {#use-the-docintel-workspace-to-classify__ul_zdz_t1l_rxb} ## Layout of the Document Intelligence workspace {#use-the-docintel-workspace-to-classify__section_ics_x1l_rxb} The following image shows the Document Intelligence workspace for a document task. The workspace includes the following areas: * 1 - Thumbnail panel * 2 - Document image panel * 3 - Document controls * 4 - Classify panel {#use-the-docintel-workspace-to-classify__ul_mp2_1bl_rxb} Nota: In this view, the documents in the Classify panel are expanded so that the categories are visible. ## Thumbnail panel {#use-the-docintel-workspace-to-classify__section_vtr_3bl_rxb} In the thumbnail panel of the workspace, you can select one page from one or more multiple-page documents. The selected page is displayed in the document image panel. Selecting a page doesn't affect what is displayed in the Classify panel. ## Document image panel {#use-the-docintel-workspace-to-classify__section_kmb_jbl_rxb} The document image panel displays the page selected in the thumbnail panel. ## Document controls {#use-the-docintel-workspace-to-classify__section_vrs_jbl_rxb} When you're reviewing a document for classification, you can use various controls to rotate, maximize the viewing area, zoom, or focus on the areas that you need. ## Classify panel {#use-the-docintel-workspace-to-classify__section_j1z_jbl_rxb} The Classify panel enables you to open each document and page classification for review, including viewing the AI's recommendations. The following image shows the Classify panel with a category field for each attachment in the document task, enabling you to enter or review the category. ## Classify documents and document pages {#ariaid-title2} Classify your documents in the Classify panel. ### Antes de Iniciar Role required: sn_docintel.extraction_agent ### Por Que e Quando Desempenhar Esta Tarefa Use the following steps to apply categories to document attachments and each of their pages. In this context, a document page is the individual page object of the digital document file, as displayed in the thumbnail panel of the workspace. A document file may contain multiple logical groupings of documents (like a PDF file with several invoices, each spanning several pages). Based on the contents, apply the categorization to the document file and the file pages. If the categories are already auto-filled with values, you can review them to ensure they are correct or adjust them as needed. ### Procedimento 1. In the Classify panel, review any auto-filled categories for each document to ensure they're correct. 2. Select a category for a document by selecting the Category field. 3. Select an appropriate recommendation for the document using the recommendation list. * Begin typing in the Category field and select a recommendation from the list. The recommendation with the highest [confidence score](https://servicenow-prod.fluidtopics.net/4QN8McQ~PKPXIl4FN_OJkA "A confidence score is a measurement (percentage) of how reliable DocIntel is in providing a recommendation for a field. The higher the score, the more reliable the recommendation.") displays at the top of the list. * Select Mixed categories for a multi-page document that includes more than one document type. Otherwise, if you select a category for a multi-page document, that category is applied to all of the document's pages. * Select Blank Page for a blank page in a document. * Select No category found if you can't find a correct match. The document will be marked as complete when you move to the next Category field. {#classify-documents-and-pages__choices_j4n_wgl_rxb} 4. Select a recommendation for each page of a Mixed categories document. The page will be marked as complete when you move to the next page. 5. **Opcional:** If needed, flag the documents or pages for later attention by selecting Flag for follow-up in the options menu from the options icon ( ![Options icon.]()).