To help you learn and configure Discovery AI custom flows faster, Discovery AI includes default data extraction mappings in the base package.

1. From Conga Start, click Admin Console > Discovery AI > Admin Dashboard.
2. Click Data Extraction Setup in the left navigation bar.
   This raises the Data Extraction Setup page.

   

3. Clicking the hypertext names of any of the mappings exposes pre-configured fields and clauses. Study these to discern the structure of well-formed data extraction mappings.

1. Click the Data Extraction Setup tab in the left navigation bar to raise the Data Extraction Setup window.
2. Click the New button to raise the New Document Extraction Mapping pop-up.

   

3. Give the new mapping a name, enter a brief description, and choose a record type from the Choose database record pull-down menu. These values correspond to a particular contract or document type. For example, in a CLM deployment, this shows agreement records.
   CAUTION:

   Do not map a single provision model to more than one field or clause. If a reviewer modifies a provision model mapped to multiple fields or clauses, there will be a conflict affecting that provision model's performance.

4. Select review levels in the Choose review level pull-down menu.
   • To deactivate the requirement to review, select 0 - Skip Review. Document review will be skipped and no contract summary will be generated or saved to CLM.
     Note:

     When a skipped document is successfully extracted, the Reviewed By field remains blank and the file is assigned a Completed status. If any field's extracted value cannot be normalized to match its data type, the file is assigned a Ready for Review status and must be reviewed. On review, the document's Reviewed By field is populated by the user name of the document's reviewer.

   • To use a single-stage review process, select 1- One level - Review and Complete from the "Choose review level" pull-down menu.
   • For a more formal process, select 2 - Two levels - Review and Approve and select one or more approver names from the "Choose reviewer(s)" menu.
5. To let users to check out batches of documents for review, slide the Allow reviewers to get next batch toggle on and then set the batch size. This enables users to check out a block of records of the designated number with a single "get batch" action. Users cannot request a new batch until they review or reassign all documents currently assigned to them.
6. Under Import Options, select extraction options to make available to your users. These are:
   • OCR to import the document as searchable text
   • Automated Extraction to submit the document for AI-only extraction, or
   • Verified Extraction to submit the document for AI extraction with attorney review.
   These choices are not mutually exclusive.
7. Depending on whether this is a purchase or vendor agreement, set the Organization Role? toggle to either Buyer or Seller.
   This setting contextualizes the generative AI prompt for Insights. Depending on this setting, the customer or user is presented to the AI engine as a buyer or seller. The default position is Seller.
8. If you want reviewers to be able to extend the worksheet with additional detected provisions as described in Adding Unmapped Fields and Clauses, slide the Allow Worksheet Extension toggle on.
9. Click SAVE.

1. Click the Data Extraction Setup tab in the left navigation bar to raise the Data Extraction Setup window.
2. Click the hypertext name of the map that you will edit in the Name column.
   This raises the worksheet mapping window.

   

3. Click the WORKSHEETS tab.
4. Select the worksheet you will edit from the Choose Worksheet pull-down menu.
5. Select the Fields, Clauses, Tables, Insights, or Obligations tab, then click MANAGE PROVISIONS or NEW to raise the corresponding mapping pop-up. For fields, clauses, or insights, continue to the next step. For obligations, go to step 7. For tables, go to step 8. For insights, follow the process described in Insights Setup.
6. Selecting Fields or Clauses opens a window marked "Choose a mapping type and an extraction method."
   1. If you select a clause provision model, you will also see an "Automatic Clause Comparison" toggle. Activating this enables automatic clause comparison for all documents with extractable clauses during import. If this is turned off, the reviewer does not see a summary of clause similarities and differences for every imported document they review. However, this comparison feature remains available on reviewer request.
      See Reviewing Imported Clauses and Fields for more.
   2. Select either Auto Extraction or Manual Extraction.
      CAUTION: If you select Manual Extraction, you will lose any configuration information for this mapping.

      Manual extractions require no further provision model configuration.
   3. Select Make this Required Field to make the extraction required.
      If the extraction is required, the reviewer cannot close the review without a value for the provision.
   4. Enter the default value. If there is no extraction, this value is assigned to the provision.
      This field must have a value for workflows set to Skip Review (review level 0).

      Note:

      When a default value is assigned to a provision, it appears in the reviewer's Provisions Found section, clearly marked as a default value. A default value does not fail validation checks for required fields.

      • If the reviewer modifies the default value or marks it as reviewed, the updated value is saved to the agreement record.
      • If the user does not modify the default value or mark it as reviewed, the default value is saved to the agreement record.

      Default values are not sent to the AI engine for training.

   5. Select the provision models to apply from the Available Provisions list and click the right-arrow icon to move them to the "Mapped Provisions:" list.

      
      
      

      Tip:

      • You can narrow your provision model choices dramatically by entering one or more words in the search bar.
      • Hovering over a provision model type in the Available Provisions column raises explanatory text describing the model.
   6. For clause extractions, you must also choose whether to extract the complete paragraph in which the clause is found. If this is unchecked, the AI will extract only the matched text.
   7. For fields associated with lookup values (values already defined in CLM), an additional control, Allow to add new record appears. Select this if you want reviewers who encounter lookup values to be able to add lookup values from CLM to the extraction. If this is selected, you must select the associated lookup fields from the Account Values drop-down menu. The reviewer will have to enter these fields manually to generate a new record.
      Note:

      • You can configure at most 70 fields and clauses in one mapping.
      • You can configure no more than ten insights in one mapping.
7. For obligation extractions, clicking the Obligations tab raises a grid view of existing obligations. Click the obligation you will edit, then the More icon (), then select Edit to raise the obligation edit pop-up.

   

   You can choose either Auto-Extraction or Manual Extraction.

   Note:

   • Obligations are fully defined in CLM. This setting controls the one feature that Discovery AI introduces. For more on configuring obligation objects, see Obligations.
   • You can configure at most ten obligations in one mapping.

   • You can introduce at most five fields per obligation.

8. Selecting Table from the New Provision window opens a Choose Table drop-down menu and suppresses the Language, Accuracy, Confidence, and Minimum Extractions to Display fields. Pick the table you will use from the Choose Table drop-down menu. The tables you can select here must already be defined in CLM. Click NEXT.

   and select a table alignment from the Default Table Alignment pull-down menu.

   Your choices are Vertical, Horizontal, and Auto Detect. A vertical table organizes like-defined elements in columns below a heading row. A horizontal table organizes like-defined elements in rows after a heading column. This selection applies to all tables in the extracted document. If you do not know what to expect or if the document presents a mixture of these types, select Auto Detect. This will increase processing time.

   Note:

   • You can only map one CLM object per table mapping. You cannot map two tables with a common agreement line item in one mapping.
   • You can configure at most ten tables in one mapping.

   • You can configure at most ten columns per table.

9. Click DONE to save the mapping.

1. Click the Data Extraction Setup tab in the left navigation bar to raise the Data Extraction Setup window.
2. Click the name of the map with the worksheet you want to clone.
3. Click the Worksheets tab.
4. Select the worksheet you want to clone from the Choose Worksheet drop-down menu.
5. Click WORKSHEET ACTIONS > Clone.
6. Enter a name for the worksheet, select the target record type, and check the component you want to clone.
   You can clone any or all of the clause, table, field, insight, and obligation components.
7. Click SAVE.