home

Discovery AI for Salesforce

Adobe Sign ServicesAiMeAdvantage Platform AdministrationAgreementsApprovals for Advantage PlatformApprovals for SalesforceBilling for Advantage PlatformBilling for SalesforceCLM for Advantage PlatformCLM for SalesforceContracts for SalesforceCollaborateComposer for Advantage PlatformComposer for SalesforceContractsConga for Google DocsConga Upgrade ProgramContract Intelligence (Standalone)Contribution Management SystemCPQ for Advantage PlatformCPQ for SalesforceDeal MaximizerDigital Commerce for Advantage PlatformDigital Commerce for SalesforceDiscovery for Advantage PlatformDiscovery AI for SalesforceDocusign ServiceseSignature Integration with Advantage PlatformGridInvoice GenerationMix FormsOrchestrateOrder Management for Advantage PlatformOrder Management for SalesforcePartner Commerce for Advantage PlatformPartner Commerce for SalesforcePrice ManagementPrice OptimizationPricing Solution SuiteQuote GenerationReal Time Pricing EngineSign for Advantage PlatformSign for SalesforceSmart CPQSmart SearchSubscriptionsTest AuthorTransportation and LogisticsTurboEnginesX-Author for Contracts 1.0 (Classic)X-Author for ContractsX-Author for Contracts Advanced for Advantage PlatformX-Author for Contracts Advanced for SalesforceX-Author for Excel for SalesforceX-Author for Migration Manager for Advantage PlatformX-Author for Migration ManagerRelease NotesGeneralDocs by Release
Adobe Sign ServicesAiMeAdvantage Platform AdministrationAgreementsApprovals for Advantage PlatformApprovals for SalesforceBilling for Advantage PlatformBilling for SalesforceCLM for Advantage PlatformCLM for SalesforceContracts for SalesforceCollaborateComposer for Advantage PlatformComposer for SalesforceContractsConga for Google DocsConga Upgrade ProgramContract Intelligence (Standalone)Contribution Management SystemCPQ for Advantage PlatformCPQ for SalesforceDeal MaximizerDigital Commerce for Advantage PlatformDigital Commerce for SalesforceDiscovery for Advantage PlatformDiscovery AI for SalesforceDocusign ServiceseSignature Integration with Advantage PlatformGridInvoice GenerationMix FormsOrchestrateOrder Management for Advantage PlatformOrder Management for SalesforcePartner Commerce for Advantage PlatformPartner Commerce for SalesforcePrice ManagementPrice OptimizationPricing Solution SuiteQuote GenerationReal Time Pricing EngineSign for Advantage PlatformSign for SalesforceSmart CPQSmart SearchSubscriptionsTest AuthorTransportation and LogisticsTurboEnginesX-Author for Contracts 1.0 (Classic)X-Author for ContractsX-Author for Contracts Advanced for Advantage PlatformX-Author for Contracts Advanced for SalesforceX-Author for Excel for SalesforceX-Author for Migration Manager for Advantage PlatformX-Author for Migration ManagerRelease NotesGeneralDocs by Release

Conga Product Documentation

Welcome to the new doc site. Some of your old bookmarks will no longer work. Please use the search bar to find your desired topic.

Show Contents

Show Page Sections

Discovery AI for Salesforce

Setting Up Discovery AI

Custom Provision Models

Provision models are available from built-in libraries. Syncing the Provision Library to the publisher (AI provider) makes these provision models available for data extraction mapping. However, if your contract's provisions do not conform to any of these pre-configured provision model types, you can name, build, populate, and train the AI on your own custom provision models.

Before You Begin

Custom provision models are a powerful approach to extracting data from contracts and supporting documents. Getting the most out of this feature requires familiarizing yourself with the underlying objects that Discovery AI can extract. All provision models must have a unique name and a defined data type. Available data types are: Date, Organization, Currency, Duration, Number, Percent, Picklist, Short Text, Multi Picklist, Text, Table, and Obligation. These describe CLM data fields to which Discovery AI must assign passages extracted from contracts and supporting documents. Your ability to define custom provision models depends on these data types being defined clearly in CLM.

Language Support

Discovery AI relies on several large language models to operate. Because AI relies on LLMs, and because the body of ingested language varies with the popularity of the language, Discovery AI's accuracy and speed across languages is not uniform. This will improve with time, but the basic requirements for constructing custom models remain important: use examples, prompts, and instructions in the language to be extracted, keep prompts and instructions as brief and unambiguous as you can, and be prepared to iterate if you find Discovery AI's limits.

To add a custom provision

Successive generations of Discovery AI have progressively reduced the resources required to train an AI to recognize and extract values from documents. Generative AI reduces the training requirement to zero. The administrator configures the generative AI search with two examples. Once the examples are added and the provision is saved and mapped to a worksheet, no additional user training input is expected: the provision extracts from imported documents automatically.

Warning:

There is an issue with custom provisions using generative AI. When the user reviews clauses from an extracted document, the on-screen highlight may not match the information gathered correctly by the AI-generated provision. This issue affects only clauses, not fields. It is scheduled for repair.

Before adding custom provisions with generative AI, alert users to this issue.

  1. From the left navigation bar of the Conga Start window, select the menu icon () and then pick Admin Apps.
  2. Click the AI icon () in the left navigation bar to open the Discovery AI admin/management view.


  3. Click the Admin Dashboard button to raise the Discovery AI Admin Home page.
  4. From the Admin Dashboard (Admin Home), click the Provision Library tab in the left navigation bar to open the Provision Library.
  5. Review the existing provisions carefully to ensure that the provision you want isn't already provided. Entering key terms in the Search & Filter field at right is a good way to shorten the list of provisions to review.
  6. If the provision you want isn't available, click the NEW PROVISION button to raise the Create New Provision window. Enter the new provision's name and select the annotation data type. Further choices depend on this selection. From the available choices (Date, Organization, Currency, Duration, Number, Percent, Picklist, Short Text, Text, Table), Picklist and Table offer additional settings.


    1. For all except Picklist and Table, select the language, minimum accuracy threshold, acceptable confidence score, maximum extractions to display for review, and enter a description of the provision. Alphanumeric characters are allowed. Duplicate provision names are also allowed.
      Tip:

      Enter clear, natural, space-separated names in the Name field, which prompts the generative AI model in the background.

      Do:

      Effective Date

      Don't:

      Effective_Date1

      E.Date.Custom

      The Description field conveys the provision's meaning to the generative AI model. In this field, provide clear phrases that describe what is to be extracted from the document. For example, the description offered to extract the effective date only if it is mentioned might be: “The date on which agreement becomes effective”. If you also consider the contract date as the effective date, the description might be: “The date on which the agreement becomes effective or is entered into.”

    2. For Picklist data types, select the data type (Date, Organization, Currency, Duration, Number, Percent, Short Text, or Text) and enter comma-separated values in the Add values for picklist field.
    3. For Table data types, select a preconfigured table from the Choose Table field.
    4. For all data types except Table, you must select a language (default: English) and you may adjust the Minimum Accuracy Threshold (expressed as a percentage), the Acceptable Confidence Score (a decimal between 0 and 1), and the Maximum Extractions to Display for Review. For more on these, see Minimum Accuracy Threshold: Theory, below.
    5. Click NEXT.
  7. The Provision Example window prompts you to add two new examples. Click ADD EXAMPLE.
  8. If any examples are available, they are displayed in the resulting New Provision window. Otherwise, you must click NEW to add an example.
    1. In the "Add example" pop-up, enter (or paste in) the paragraph text you will extract and the data you want to extract.
      Tip:

      For fields, enter the sentence, paragraph, or clause where the field is usually found in the Paragraph Text field.

      For example:

      This agreement is entered into on 1/1/2024 by and between ABC Inc., a Delaware company, and XYZ LLC, headquartered in San Jose.

      In this example, enter 1/1/2024 in the Data to Extract field.

      For clauses, enter a sentence, paragraph, or clause in the Paragraph Text field that is similar to or exactly the clause to be extracted.

      For example:

      No Party shall be liable or responsible to the other Party, nor be deemed to have defaulted under or breached this Agreement when delay is caused by or results from acts of God.

      In this example, enter the same clause information in the Data to Extract field, as the extraction involves the entire clause or paragraph.

    2. Click Add another example and repeat the preceding substep with another example. You must provide at least two samples for the AI to work.
    3. Click ADD.
  9. Your entry is now available in the Examples table.
  10. When you have entered all your examples, click DONE.
    You will receive a success message and see a summary of the new provision.

Your new custom provision is available in the Provision Library and is active by default.

When you activate the provision, it becomes available for inclusion in worksheets. Once the new provision is introduced to an operating worksheet, users can see the provision and train the AI on it.

There is no manual training flow. If the AI does not produce the desired accuracy, add more examples to the provision as described above.

To add a custom provision

  1. Click the Provision Library tab in the left navigation bar to open the Provision Library.
  2. Review the existing provisions carefully to ensure that the provision you want isn't already provided. Entering key terms in the Search field is a good way to limit the list of provisions.
  3. If the provision you want isn't available, click the NEW button to raise the Create New Provision window. The DETAILS & SETTINGS tab is available and the TRAINING and ANALYSIS tabs are disabled.


  4. In the DETAILS & SETTINGS tab:
    1. You must enter a name and a brief description for the new provision (Alphanumeric and select special characters are allowed. Duplicate provision names are also allowed). Select the data type (Date, Currency, Duration, Number, Percent, Picklist, Short Text, or Text).
    2. You must set a minimum accuracy threshold (this is expressed as a percentage) and select the language in which the anticipated contracts are written. The minimum accuracy threshold is the AI review's F1 score, expressed as a percentage. The machine learning model uses this value to determine whether to publish the custom provision and to set its status to Trained when it publishes it. Setting this too low valorizes training speed over precision. Setting it to 100 ensures that the provision can never leave training. Conga recommends setting this value to 65 as the best practice for balancing training efficiency and precision. For more detail, see Theory, below.
      1. Set the value to 80% – 90%+ for extractions to begin only when the AI model has high confidence.
      2. Set the value to 65% – 70% for extractions to begin even when some results may be wrong.
    3. You can speed up training by selecting a provision from the Based on Provision field and thus basing the custom provision on an existing one that is "close" to it. If your custom provision were, for example, an indemnity provision with a specific added third party, you can configure the AI to look for an indemnification clause first, then to search specifically for the peculiar third-party character of your custom provision. This makes it much easier for your users to train the AI, as it puts them "in the ballpark" without forcing them to search for the provision in the contract, and they can highlight the exact passage for training from the section already located by the "based on" provision.
      In the following example, the Custom_LicenseDate provision is created using the Based on Provision field to use the existing trained provision, C_AD_License_Date.


    4. You may enter one or two examples of the provision text. These examples are optional, and for human readers to identify and understand the provision. They are not for the benefit of the AI.
    5. Set the Maximum Extractions to Display for Review field to a value that makes sense for the number and complexity of extractions you anticipate when users will review this provision.
    6. The Active toggle is ON by default. To revisit the Details and Settings window before training, slide it off.
    7. Click Save.

When you activate the provision, it becomes available for inclusion in worksheets. Once the new provision is introduced to an operating worksheet, users can see the provision and train the AI on it.

Training

When the total count of annotations reaches 30 for a provision, training automatically begins. You can also trigger training for a provision before 30 annotations are entered by force-training the AI on a limited set of annotations.

To manage training tasks

  1. Open the Provision Library and select a provision as described in To review annotations.
  2. Click the TRAINING tab. The Training in Progress pane at left describes the documents containing the subject provision that have already been annotated and the total number of annotations in the reviews. The Still to Be Trained pane accounts for remaining annotations and documents.
  3. Flipping the Stop retraining toggle on forces to AI to use the training it has already received to find future provisions. This reduces review latency but may cost accuracy if turned on before the AI is fully trained.
  4. AI training normally activates after 30 annotations (thumbs-up/-down marks, text selections, or selection edits) have been entered. Clicking the FORCE TRAIN button pushes the AI out of training mode immediately. This may save time but may also cost accuracy.
    Note: Force-training with fewer than five annotations is not recommended.

Training

Each provision must be trained on a body of documents to reach a desirable level of accuracy. This training is performed by users working through a conventional review process.

The Force Training feature shortens the training period to a configurable number, lessening training period overhead.

To force-train a provision

  1. From the Conga Start page, click Admin Apps.
  2. Click the AI icon () to open the Discovery AI admin/management view.


  3. Click the Admin Dashboard button to raise the Discovery AI Admin Home page.
  4. Click the Provision Library tab to open the Provision Library.
  5. Find the provision for which you will configure training and click the link text to open the provision to the DETAILS & SETTINGS tab.
  6. Click the TRAINING tab to raise the training window. This window reports the number of documents included and queued for training.


  7. Clicking the FORCE TRAIN button sets the provision to a Trained state. By default, training commences when 30 documents are queued.
    Note:

    It is a best practice to wait for five provisions to have been reviewed before force training. Force training prematurely will compromise accuracy.

  8. You can set the retraining toggle to stop or continue retraining. This feature feeds training results back to machine learning to enhance accuracy. Once you achieve a desired level of accuracy, you can switch this off.

Minimum Accuracy Threshold: Theory

It is important to have a working understanding of the accuracy and confidence scores, as these are the final criteria by which you will measure the AI's performance in recognizing your custom provision. As the F1 score is a factor of accuracy, precision, and recall, it is worthwhile to have a basic understanding of these foundational concepts. Once a provision is trained enough to produce a meaningful statistical sample, you can fine-tune the results based on the AI model's confidence score.

Accuracy

Accuracy describes the ratio of true positive and negative identifications for all samples. The ratio of true positives detected to all actual positives is classified as Recall . The ratio of true predicted positive results to all (true and false) predicted positives results is called Precision. These are combined to form an F1 Score.

Precision

Precision is a measure of the AI's predictive correctness. For example, if the AI is asked to find apples in a mixed basket of fruit, a perfect precision score of 1.00 means every fruit it found was an apple. This does not indicate whether it found all the apples. Expressed mathematically:

precision = true positives / (true positives + false positives)

Recall

Recall is a measure of completeness. For example, if the AI is to find apples in a mixed basket of fruit, a perfect recall score of 1.00 means it found all the apples in the basket. This does not indicate it found only apples: it may have found some oranges too. Expressed mathematically:

recall = true positives / (true positives + false negatives)

Categorizing legal concepts has more variation than picking fruit, especially when the provisions are reviewed by different legal professionals; therefore, recall and precision may differ among annotators (one person's recall of 0.90 may be someone else's 0.80). Remember this when using built-in provisions and reviewing annotations.

F1 Score

The F1 score is the harmonic mean of precision and recall. It provides a more sensitive measure of accuracy than precision or recall alone. Expressed mathematically:

F1 = 2 * [(precision * recall) / (precision + recall)].

The F1 score gives equal weight to both precision and recall for measuring a system's overall accuracy. Unlike other accuracy metrics, the total number of observations is not important. The F1 score value can provide high-level information about an AI model's output quality, enabling sensitive tuning to optimize both precision and recall.

When setting up custom provisions, you are asked to enter a desired minimum accuracy threshold. This is an F1 score, and Conga recommends you set this value to 65, which we have found optimally weights AI precision vs. trainer time.

Prediction Threshold

Also called a confidence threshold, this is presented in our app as the Acceptable Confidence Score. This value describes a confidence level above which information is accepted and below which it is rejected. If the threshold is set to 0, all responses exceed the threshold and are accepted. If the threshold is set to 1, then no response exceeds the threshold and all are rejected.

In general:

  • Increasing the prediction (confidence) threshold lowers recall and improves precision (i.e., biases towards true positives, but throws some good results away).
  • Decreasing the prediction threshold improves recall and lowers precision (i.e., biases towards including more hits, but with more false positives).

If you find your results have a lot of false positives (Discovery AI identifies incorrect passages as matching results), raise the prediction threshold setting. If you find the AI is missing too many entries, i.e., not detecting passages as matching, lower this setting.

Deleting Custom Provisions

You can delete custom provisions from the Provision Library. You cannot delete provisions synced from a publisher.
  1. Open the Provision Library and find the custom provision you will delete.
  2. Check the box adjacent to the provision or provisions you will delete.
  3. Click the Delete button.
  4. The Provision Library screen automatically refreshes itself. Review Provision Library to verify that the provision or provisions are removed.

Configuring a Custom Provision with Table Extraction

You can use AI to extract tables from documents. This is especially useful when contracts present such tabular data as bills of materials or delivery schedules. Because table extraction requires generative AI, these extractions do not require training. Users can extract tables as soon as the table extraction is configured and mapped to a worksheet.

Each table must have a columnar structure, with each line reflecting the values named in the heading. Discovery AI extracts these values in much the same way it handles fields and clauses, presenting this data in a column-defined line-item format.

  1. Follow the procedures for To add a custom provision (above) to step 6c.
  2. Select Table from the Annotation Data Type drop-down menu.Some screen options (Based on Provision, Minimum Accuracy Threshold, etc.) disappear.
  3. Select a table by name from the Choose a Table drop-down menu. These tables are defined in CLM. You can set up new tables in CLM by following the instructions for adding contract line items.
  4. Click Next.
  5. Click ADD COLUMNS to raise the Add Alternate Keywords for Columns pop-up.
  6. Select a column name from the Choose Column drop-down that you want the AI to extract. This populates the adjacent Add Values for Keywords cell.
  7. Click the NEW COLUMN button to add columns to extract. Add columns in the order you want this information presented. The order you see here is the presentation order of the extraction, irrespective of the order the columns fall in the scanned table. You are not required to select every column.
    Note:

    The order of the columns here controls the order in which they are presented to the reviewer. To change the order, you must delete and add columns until you achieve the desired order. It is therefore a good idea to have the presentation order in mind before you begin.

  8. You must click the checkbox adjacent to one of the columns to set it as the primary column. This identifies the essential property of the line without which there would be no line. For example, on a line containing the column heads "Deliverable", "Quantity", and "Unit Price", the Deliverable column is the reasonable primary choice, as there is no quantity or price without a deliverable product. Primary selection does not affect the presented order of the columns, but it is the "handle" by which reviewers will access and sign off on the extracted data.
  9. For each column, enter keywords as comma-separated text in the Add Values for Keywords field approximating likely column headings to enhance the AI's likelihood of accurate extraction. For example, if you know a column normally titled "Description" is occasionally titled "Desc.", you can enter that alias here.
  10. You can check the Strict Name Match box to enforce verbatim column-heading matches. Leaving this unchecked permits AI matching.
  11. If the table type contains hierarchic data, indicated by regularly indented rows in existing columns, you can set a hierarchic value for the column entry. For example, if a table has a column named "Prices" with sub-entries for "$1–$5,000", "$5,001–$10,000" etc., you can select the Prices column from the Choose Column field, populate the Add Values for Keywords field with entries of "$1–$5000", "$5001–$10000", and so forth, and assign Hierarchy level 1 in the Type field.
    Note: Do not enter values with commas except to divide entries. Entries in the Add Values for Keywords field are comma-delimited, so your entries will be broken into fragments at each comma.
  12. When you have selected and described all columns desired for extraction, click ADD to review your columns.
  13. You can slide the Match exact column count toggle to ignore tables with an unexpected number of columns.
  14. Click DONE to save the new custom provision and return to the Provision Library.
Administrator Guide
Contract Intelligence
Discovery

August 18, 2026