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 Page Sections

Document Review

Discovery Agent can automatically identify document types and configure itself to extract data from contracts and third-party paper using artificial intelligence and machine learning to compare scanned text to provision models. Reviewers monitor the results, verifying and correcting them where necessary. Different provision models extract different types of data and present different workflows.

Reviewing Imported Clauses and Fields

You have logged into Discovery Agent as a reviewer as described in Accessing Discovery Agent and are at the Home page.

You can review and correct the clauses and fields extracted from imported documents. Discovery Agent converts all scanned or uploaded documents to PDF format for scanning and review. Provisions and other significant text are highlighted for review in an in-app PDF reader, and each is displayed in the column to the right in the order it appears in the document. For each detected clause or field you review, you can accept the extract, reject the extract, edit the extract, or flag the extract for review.

  1. From the Home page, click the name of a file marked “Ready for Review.” Alternatively, you can click the folder icon to access the Project Dashboard, open a folder, and click the name of a file marked “Ready for Review.”
    The selected document opens for review. The extracted document appears to the left, with review options to the right. The default selected option is Review. From this view, you can access tabs for Details, Insights, and Review History. From the Review tab, you can access sub-tabs for Summary, Fields, Clauses, Tables, and Obligations. The Fields tab opens in the default view.
  2. Passages from the extraction map that the AI has identified are highlighted in the text and identified by mapping category under the Provisions Found heading in the review column to the right.

    For example, if a contract contains an amended effective date field, as has been mapped in the extraction map, that field is highlighted in the text and appears in the right column under its field-name heading. Provisions found in the contract are exposed in the review panel in the order they appear in the contract.

    CAUTION:

    When a clause spans a page break, Discovery Agent may ingest header or footer material as part of the extracted clause language. If this happens, edit the extraction by hand to remove the extraneous information and do not re-highlight it.

  3. The AI tracks its reason for extracting a field or clause, which you can review by clicking the yellow light-bulb icon () next to the extraction.
  4. For found provisions, you can offer feedback on extraction quality directly to the AI (using the thumbs-up and thumbs-down icons), mark a field or clause as reviewed (approved), or flag the entry for further attention.
    Note:
    • Offering feedback is optional, but helps train the AI to make more accurate extractions.

    • Thumbs-down reports are stored, and this feedback informs the AI for both clause- and field-type provision models. ​

    • It’s best not to give negative feedback to clauses for which the Extract Full Paragraph option has been set,

    • If the AI is close to correct, it’s better not to give negative feedback. You can delete the extraction, highlight the good text, and give a thumbs-up to the edited result.

    The AI’s confidence score is indicated on the left, using color-coded bars:
    Hovering over the lightning icon indicates how the provision was extracted.
    Possible sources are:
    • AI Pipeline: Results are from an automated extraction. These are AI extractions from built-in and custom provision models that use no key phrases or AI prompts. For custom provision models, the AI pipeline may use the administrator-supplied Special Instructions text to fine-tune extractions.
    • Key Phrase Search: Results are from an extraction in which the AI relied on key phrases to improve its accuracy.
    • Advanced AI: Results are from an extraction informed by AI prompts.
    • User Annotation: This extraction was manually annotated by a reviewer.

    Mandatory fields are indicated by “Required” indicators:

    Your review cannot be completed until these required values are populated, either automatically or through manual editing.

  5. Provisions that were not found in the extraction are indicated in the Provisions Missing section (below Provisions Found). For each of these provisions:
    1. Review the scanned contract text at left for the passage that will satisfy this provision description.
      Tip:

      You can speed this up using the in-app document search feature (the magnifying-glass icon () at top left).

    2. For each passage you find, highlight the passage, then right- or control-click the highlighted text to raise the selection pull-down. Pick the provision model that matches the highlighted passage.

      For complex extractions where the list of available clauses or fields may be voluminous, you can enter the provision model name or a portion of it in the Search field to narrow your options.

    3. Alternatively, you can copy the highlighted text and paste it into the appropriate provision model field.
  6. Select each item to raise a summary of the field, clause, table row, or obligation item’s name and a comparison of extracted values and their interpreted value.
    Extracted clauses are compared to standard clauses and the match/non-match results displayed.
  7. When the AI extracts documents, it compares the ingested text to known samples to find matches and close correlations to sample provisions. Use the Compare or Edit Clause feature to review its performance, learn how it makes such comparisons, and select the best of several alternative clauses.
    Clicking the down-arrow icon adjacent to an extracted clause exposes standard clauses, which are stored in the Clause Library as standard text. If no standard text is stored, this will be blank and the AI will not find similarities or differences that it recognizes as close matches.


  8. Click Compare or Edit Clause to expose the Clause Assignment window, with Extracted Clause and Standard Clause tabs.
    1. The Extracted Clause tab shows the extracted clause itself.
    2. Click the Standard Clause tab to review the standard clause to which the extracted clause was compared (this can include the language of custom provision models).
    3. Click Compare with Standard Clause to display an AI-generated comparison of the similarities and differences between the extracted clause and the standard.
      For some implementations, AI comparison is on by default: the comparison is generated when the document is extracted. If automatic AI comparison is not enabled, you must click through, triggering AI comparisons as needed.
  9. When you have reviewed and validated all values, click Review Complete.
    CAUTION: This action is irrevocable. Once you mark a document as approved, you cannot edit it any further.

Reviewing Imported Tables

You have logged into Discovery Agent as a reviewer as described in Accessing Discovery Agent and are at the Home page.

You can review and correct tables extracted from imported documents.This review process is similar to that for clause and field extractions, though the table form requires extra considerations. For each detected table you review, you can accept, reject, edit, or flag the extract for review by line or by table (bulk review).

  1. From the Home page, click the name of a file marked “Ready for Review.” Alternatively, you can click the folder icon to access the Project Dashboard, open a folder, and click the name of a file marked “Ready for Review.”
    The selected document opens for review. The extracted document appears to the left, with review options to the right. The default selected option is Review. From this view, you can access tabs for Details, Insights, and Review History. From the Review tab, you can access sub-tabs for Summary, Fields, Clauses, Tables, and Obligations. The Fields tab opens in the default view.
  2. Click the Tables tab.
    Extracted tables are listed below the Tables tab. Tables are extracted as several expandable rows of fields and displayed individually:
    Note: If a table defined in the provision model has not been extracted, you can select the table text in the document panel, assign it to the table provision model that should have picked it up, and add the table data manually.
  3. Hover over the table name and click the Review/Edit Table text.
    The selected table’s table extraction appears below the document review pane, open to the default Review/Edit view.
  4. Click Review/Edit Table to raise a half-screen user interface for reviewing the table rows. The table display includes the page number (as scanned) in the contract on which the table appears.
    Note:

    When you click on the Review/Edit Table link, the document view may not be updated to the table’s location. If this happens, click again, or click the name of the table.

  5. For each row, you can:
    • Double-click line items to edit individual values.
    • Use the up or down arrow icons to reorder the rows.

    • Click the plus-sign icon to add a row below the selected row.

    • Click the trash-can icon to delete the row.

  6. When several rows must be corrected in the same fashion, select those rows, then click the pencil icon to perform a bulk edit.
  7. For each column heading represented in the bulk edit pop-up modal, select only those values you will edit. Do not click the select box for valid values. Only the values you select here are subject to change. If you select a value and then do not enter information in its frame, the value in the extracted table will be overwritten with nothing.
  8. You can review your progress by clicking the Preview tab.
  9. When you have reviewed one, several, or all rows, click Mark as Reviewed.
    CAUTION: This action is irrevocable. Once you mark a row as approved, you cannot edit it any further.
  10. When you have reviewed, edited, and approved the table, click Done.
    You are returned to the Review/Tables view

Searching Document Text

While reviewing a document under extraction, you can search the document text.

Finding text pertinent to your extraction may require searching the document text itself.
  1. Open a document for review from either the Recently Updated Documents table on the Home page or the Project Dashboard’s Document View.
  2. Open the Review interface as described in Reviewing Imported Clauses and Fields.
  3. Click the magnifying glass icon () at top left.
  4. Enter your search term.
    Searched strings are highlighted in the document.
  5. You can select Highlight All or Ignore Case to change the search’s presentation and case-sensitivity. You can also reverse search order using the up and down arrows.

Document Summary

A document summary is located under the Review tab.

The AI engine generates a summary field for all documents, except those ingested as OCR-only. A document under summary is indicated as a blank in the review interface with a spinner running. You can click the pencil icon to edit the generated summary.

Note:
  • The document is summarized when you open it for review.
  • Longer documents take longer to summarize.

If there is a summary error, you are warned and asked whether to complete the review when you attempt to save. If you affirm, the review is saved with no summary. If you decline, the save aborts. The Summary tab offers a Regenerate button to retry the summary or you can enter one by hand.

Use Case

A general counsel with a pre-negotiation briefing in 15 minutes needs to understand the key terms of a 120-page distributor agreement without reading it. Opening the document in Discovery Agent, they read the two-paragraph AI-generated summary under the Summary tab and then skim the risk flags in Insights. The counsel walks into the meeting informed, having spent four minutes in Discovery Agent, rather than four hours with the original contract.

Searching Provisions

You have opened a document extraction for review.
For complex extractions, you can use a search feature to make finding provisions easier.
  1. Click the search (magnifying glass) button to open the provision search feature. This helps you narrow the list of visible provision model entries in the review column. You can also find issues more effectively by sorting provisions in ascending or descending order.


  2. For each entry in the review column, you can click the down arrow to expand it, exposing the text of the found provision and some review tools.


Adding Unmapped Fields and Clauses

You can map new fields and clauses defined in CLM that are suggested by Discovery Agent from the review page.

If the administrator has enabled it, you can extend the provision models mapped for a document you are reviewing as suggested by Discovery Agent. When you import a document, Discovery Agent finds CLM fields and clauses that have been mapped and indicates which ones it has and has not found. On your request, it can display provisions that have not yet been mapped as suggestions. This feature works for fields and clauses, but not for tables or obligations.

You can review and add unmapped fields and clauses from the extraction to the worksheet before saving them to CLM. Adding an unmapped value maps the subject passage to the provision map, tying it to the fields, clauses, or values available in the CLM schema. Subsequent imports will include the new provision models and use them in extractions; however, this mapping is not retroactively applied to already-imported documents.

Use Case

A paralegal reviewing a newly onboarded software license agreement notices that it contains a “Source Code Escrow” clause, a provision that is absent from the standard software agreement worksheet. Rather than flagging it for later, she clicks Add Unassigned Clauses to map it to an existing CLM clause field in real time. The next import of a software license using this worksheet will include looking for this clause provision model as part of its review.

  1. Enter the review flow as described in Reviewing Imported Clauses and Fields.
  2. Click the Add Unassigned Fields or Add Unassigned Clauses button at bottom right.
    This raises the Manage Mappings window.
  3. In the Manage Mappings window, select a field or clause from the Select Field or Select Clause column at left. For fields, the appropriate data structure (Boolean, date, number, etc.) populates the Default Value field.
  4. For each extraction, you can select either manual or automatic extraction (auto-extraction is the default) and whether the field is required.
  5. When you have selected the correct provision model, click its right-arrow button to send it to the Mapped Provisions column.
    Note: If you map a single provision model to more than one field or clause, a conflict can result if the reviewer changes the text of one of those fields or clauses. For this reason, it’s best not to not map one provision model to multiple fields or clauses unless they represent the same thing.
  6. Click DONE.
    The new extraction is added to the set of extractions for Discovery Agent to perform and to the CLM database to save.
  7. Continue your review as described in Reviewing Imported Clauses and Fields with the new provision model added as a missing provision to the column of provisions to review.
The selected field or clause mapping is added to the associated worksheet and displayed under PROVISIONS MISSING. When you have annotated the mapping, assigned it to this field or clause, and completed the review, this value is saved back to the CLM agreement record. Discovery Agent will extract this field or clause from subsequent imported documents of this type.

Adding New Clauses from Reviewed Documents

You can create new clause provision models based on passages you highlight while reviewing.

As a reviewer, your main task is to validate extractions based on pre-configured provision models. If your instance is configured to permit it, you can also map a clause or field that conforms to an unmapped provision.
  1. Enter the review flow as described in Reviewing Imported Clauses and Fields.
  2. Highlight a passage of interest in the document.
  3. Right-click the highlighted passage and scroll to the bottom of the drop-down menu.
    Note: It is a good idea to review the available pre-configured provision models in this menu to see if your selection conforms to any of the mapped provision models.
  4. Click +NEW CLAUSE.
    The Add New Clause window opens with the highlighted text automatically populating the Clause Text field.
  5. Enter a name for the new clause and click SAVE.
    Your new clause appears under the Clauses tab of the review panel at right.
  6. Complete your review as described in Reviewing Imported Clauses and Fields.
  • Your selected passage is now a clause provision model.
  • Your new clause is entered into CLM.

The new provision model is not automatically added to any worksheet. To do this, follow the instructions in Editing a Data Extraction Mapping, adding your new clause.

Details Tab

The Details tab, adjacent to the Review tab in the document review interface, contains these fields:

  • Document Name
  • Record Type
  • Worksheet Name
  • Review Level
  • Review completed by
  • Owner
  • Assignee
  • Document comment

The Document Name, Worksheet Name, Review Level, “Review completed by”, and Owner fields are populated from the back end. You can select the record type and assignee and enter comments in the “Document comment” box.

Editing an Extracted Provision

You can edit or manually populate each provision entry.
  1. From the Project Dashboard or the Home screen, open a Ready for Review document as described in Reviewing Imported Clauses and Fields.
  2. Click the "down" arrow () to open the entry.
  3. Click the edit (pen) button to open the provision for editing.
  4. Edit the provision (This edits the clause, field, or line item's metadata, not the contract text).
    Note:

    The Administrator may have configured the provision model to insert a default value if Discovery Agent could not find the provision text in the document. Such values are clearly indicated in the reviewer UI. You can edit these provisions like any other.

  5. Edit another entry or click MARK AS REVIEWED.
    Marking an entry as reviewed is not required to complete the review but is useful for tracking it.
  6. When you are done editing, click the Accept (check mark) button, confirming that it has been accurately extracted, marked, and categorized. To abort the edit, click the X.

Deleting One or More Provisions

You can delete an unsuitable or inaccurately extracted provision from your results.

Review the fields, clauses, tables, and obligations configured for document extraction. If you discover an error in the extracted data that is better served by a fresh start, you can delete the extraction.
Delete a provision
  1. From the Project Dashboard or the Home screen, open a Ready for Review document as described in Reviewing Imported Clauses and Fields.
  2. If you have opened an erroneous extraction that you will not correct as described in Editing an Extracted Provision, and would prefer to delete altogether, click the More () icon to the right of the provision tile in the Review column at right and click the resulting pop-up trash-can () icon.
  3. Click DELETE in the confirmation pop-up.
Delete multiple provisions
  1. Click the checkboxes to the left of the provisions you will delete.
  2. Click the trash-can () icon above the provisions in the Provisions Found header.
  3. Click YES, DELETE in the confirmation pop-up.
The selected provision or provisions are deleted. Deleted provisions are emptied, but remain available to be identified in the document and are moved from Provisions Found into Provisions Missing in the review panel.

AiMe Assistant

AiMe Assistant is an AI-powered virtual assistant designed to boost productivity and efficiency when working with a contract document through its entire life cycle. It uses machine learning (ML) and natural language processing (NLP) to analyze and generate content. This tool enables users working on contract documents, supporting documents, and global and other documents to summarize them and to get answers about them.

AiMe:

  • Answers questions about such documents as contracts, their supporting documents, and global documents.
  • Keeps a history of questions users asked it in a document.
  • Summarizes contracts, supporting documents, and global and other documents.

Use Case

Used properly, AiMe Assistant can make the most of your time when analyzing contract documents in your workflow.

With 30 minutes left before a renegotiation call with a key supplier, a procurement manager opens the 87-page supply agreement in Discovery Agent and asks AiMe: "What are our volume commitments and what are the penalties for missing them?" and "Does this contract auto-renew?" AiMe returns precise answers to these natural-language questions, with citations in under a minute, saving considerable time and stress to search the provisions for the right fields.

Accessing AiMe Assistant

Discovery Agent can provide access to AiMe Assistant, a conversational AI that can answer questions about documents.

AiMe Assistant is a discrete AI engine for contract insights and analysis. You can access it while reviewing extracted documents. Discovery Agent’s artificial intelligence engine is constrained to extracting defined passages from documents. AiMe can answer questions posed conversationally.
  1. From Conga Start, open Contract Apps > Discovery Agent.
  2. From the Project Dashboard or the Document view, open any document in a Complete, Ready for Approval, or Ready for Review status.
  3. Click the AiMe button to the right of the review panel.
The AiMe review window opens.

Asking AiMe a Question

  1. AiMe opens with the document details on the left and the “Get answers from this contract” window on the right:


    Three buttons offer prompts pre-configured by Conga:
    • Summarize key terms: This inserts a verbose prompt directing the AI to generate a summary of the document. This prompt includes:
      • Parties involved (legal entity names, roles)

      • Agreement type (MSA, NDA, SOW, Order Form, Amendment, etc.)

      • Effective date and term/duration

      • Key commercial terms (pricing, payment terms, if visible)

      • Critical dates (expiration, renewal, notice deadlines)

      • Governing law and jurisdiction

      • High-level obligations of each party

    • Natural Language Q&A: This inserts a prompt that exemplifies the question format for a natural-language Q&A request (“What is the termination notice period?”).

    • Clause & Term Extraction: This inserts a prompt that exemplifies queries about specific provisions extracted from the contract (“Does this contract have a force majeure clause?”).

    Clicking these injects the prompt into the AI chat box.
  2. You can select a frequently used prompt configured by your administrator by clicking directly on the question as it appears in the Quick Start Prompts above the text entry box or by entering a slash in the text entry box and selecting one of the pre-configured shortcut prompts.
    In addition to direct questions about document content, AiMe can perform these simple mathematical operations in its results:
    • Matching-record counts

    • Sums and differences

    • Averages and means

    • Maximum and minimum values

    • Grouping by criteria

  3. If you have a question that is not predicted by a pre-configured prompt, enter it in the text box.
    Note:

    AiMe only answers questions about one document at a time, and the scope of its responses is limited the documents under management. It can access all .docx and .pdf files available to it in CLM.

    AiMe can respond to positive query logic (“Does the contract have a pandemic clause?”) and negative logic (“Does the agreement lack a termination date?”).

  4. Click the Send icon ().
    AiMe provides updates on its processing status as it considers your question and forms its answer.
  5. AiMe returns its answer. You can:
    • Copy the answer to your clipboard by clicking the copy icon ().
      Note: AiMe interprets copying an answer using the Copy icon () as positive feedback.
    • Regenerate the answer by clicking the repeat icon (). This re-prompts the AI with the question already asked. This is useful if you are not satisfied with the answer.
    • Offer feedback using the thumbs-up or thumbs-down icons as described in Giving Feedback. These responses are used to improve the AI and are logged for quality analytics.
  6. To clear the AiMe window for a new chat or to raise the chat history for review, click the menu icon () and select fom the pop-up menu . You can also exit AiMe altogether by clicking the go-away icon ().

Use Case: Verifying a Clause or Field

  • The user has uploaded or selected a contract document in a supported (PDF, DOCX) format.
  • AiMe has processed and indexed the document .
  • The user has appropriate permissions to view the document content.
  • The AiMe is available and responsive.

The user, a lawyer, contract manager, procurement specialist, or sales operations manager, wants to verify quickly whether a specific clause (e.g., indemnification, limitation of liability, termination for convenience) or field (e.g., effective date, governing law, notice period) exists in a contract document and if so, retrieve its exact wording or value.

  1. The user opens the contract document from the parent interface (CLM, Discovery Agent, etc.)
  2. The user enters a query in the chat box, such as: “Does this contract contain an indemnification clause?”, “What is the governing law in this agreement?”, or “Is there a limitation of liability provision?”
  3. AiMe processes the query and searches the document for relevant content, returning a response indicating whether the clause or field exists, along with the summarized text.
  4. The user reviews the extracted clause content and may follow it to the source location.
Expected Result
  • A clear yes/no confirmation of the clause’s or field’s presence.
  • A text summary of the identified clause or field value.

Alternatives or Exceptions

Clause not found: AiMe responds with “No [clause type] was found in this document”.

Note:
  • Use specific clause names (“limitation of liability” rather than “liability issues”) for more accurate results.
  • For fields, specify the exact field name as it might appear in the document (“Effective Date” rather than “term commencement”, for example).
  • Review the full clause in context before making decisions, as the excerpt may not capture all relevant conditions.

Use Case: Asking “Yes or No” Contract Questions

  • The user has uploaded or selected a contract document in a supported format.
  • The document has been processed.
  • The question can be answered based on information contained in the document.
  • The user understands that the response is based on AI interpretation and may require verification.

A lawyer, contract reviewer, compliance officer, or business stakeholder wants a yes or no answer to a specific question about contract terms, conditions, or provisions to support rapid decision-making during contract review or negotiation.

  1. The user opens the contract document from the parent interface (CLM, Discovery Agent, etc.)
  2. The user enters a yes/no question in natural language, such as: “Does this agreement allow automatic renewal?”, “Is the vendor liable for consequential damages?”, or “Can either party terminate for convenience?”.
  3. AiMe analyzes the document and returns a clear “Yes” or “No” response, followed by the supporting text from the contract that justifies the answer.
  4. The user reviews the supporting evidence, proceeding with their own review or decision.

Use Case: Summarizing a Document or Clauses

  • The user has uploaded or selected a contract document in a supported format.
  • The document has been fully processed and indexed.
  • The user has identified the specific focus area(s) or clauses they want summarized.
  • For multi-clause summary, the user can specify which clauses to include.

A lawyer, contract manager, executive reviewer, or deal desk analyst wants to accelerate their contract interpretation and review with a tailored summary of the entire contract focusing on specific user-defined aspects, or a consolidated summary of several selected clauses.

  1. The user opens the contract document in the AiMe interface.
  2. The user requests a summary with custom guidance, such as: “Summarize this contract, focusing on financial obligations and payment terms,” “Provide a summary of the termination, renewal, and assignment clauses,” or “Give me an executive summary highlighting key risks and unusual provisions.”
  3. AiMe processes the document with the specified focus on the requested clauses, generating a structured summary that addresses the user’s specific areas of interest, organized by topic or clause.
  4. The user reviews the summary, which includes references to source locations for each summarized point.

Use Case: Extracting Obligations

  • The user has uploaded or selected a contract document in a supported format.
  • The document contains identifiable party names or roles.
  • The contract includes obligation-related language (shall, must, will, agrees to, commits to, etc.)

A contract manager, compliance officer, project manager, or legal operations specialist wants to identify and extract all obligations (duties, responsibilities, commitments, deliverables, and deadlines) for each party in the contract to support obligation tracking, compliance monitoring, and project planning. Such a user might want to filter obligations by party, type, or time frame.

  1. The user opens the contract document from the parent interface (CLM, Discovery Agent, etc.)
  2. The user enters an obligation extraction request, such as: “Extract all obligations from this contract”, “What are the vendor’s obligations under this agreement?”, “List all deliverables and their due dates”, or “What must our company do under this contract?”
  3. AiMe scans the document for obligation language and returns a structured list of obligations.
  4. The user reviews the extracted obligations and can export or transfer them to an obligation management system.

Use Case: Doing Math with Table Data

  • The user has uploaded or selected a contract document containing one or more tables with numeric data.
  • The table structure is simple and clearly formatted (standard rows and columns).
  • Numeric values in the table are recognizable (not embedded in complex text or images).
  • AiMe has parsed the table content during document processing.

A financial analyst, procurement specialist, contract manager, or commercial operations manager has to perform basic calculations (sum, difference, average, count, minimum/maximum, and ratio) on numerical data from tables in the contract document to analyze pricing, quantities, or other numeric terms.

  1. The user opens the contract document from the parent interface (CLM, Discovery Agent, etc.)
  2. The user identifies a table in the document (e.g., pricing table, fee schedule, quantity list).
  3. The user enters a calculation request referencing the table, such as: “What is the total of all line items in the pricing table?”, “Calculate the average unit price from the fee schedule”, “What is the maximum quantity listed in the order table?”, or “Add the values in the Annual Fee column.”
  4. AiMe identifies the relevant table, parses the numeric data, performs the requested calculation, and returns the calculated result.

Best Practices

Rules to follow for better results

Do

  • Ask direct, factual questions based on the content present in the contract.

    Example: “What is the governing law for this agreement?”

  • Use AiMe to summarize large sections or entire agreements.
  • Phrase your prompts in a clear, natural tone. Specific, business-focused inquiries yield the best results.
  • Validate AiMe’s outputs before using them in internal or external communications.
  • Use AiMe on contract documents that are either finalized or under-negotiation, provided they are uploaded to the Agreement Documents list in a readable format.
  • Ask your AiMe admin to create shortcut prompts for frequently asked queries.
  • Use AiMe to analyze the current document only. It cannot reference or connect to external files.
  • Use AiMe to help non-legal stakeholders (sales, procurement, finance) navigate dense legal language.
  • Remember that AiMe is a summary and insight assistant, not a legal decision-maker.
  • Report recurring issues or gaps in responses to Conga.

Don’t

  • Request opinions, recommendations, or predictive analysis.

    Example: “Will this clause protect us in future disputes?”

  • Use vague or broad prompts.

    Example: “What’s important here?”

  • Ask several questions in a single prompt: AiMe may hallucinate (Ask questions separately).

    Example: “Give me the effective date, term length, governing law, payment terms, liability cap and notice period.”

  • Ask AiMe to perform complex mathematical operations or multiple operations in a single prompt. AiMe can perform basic operations on numbers in a simple table, such as sum, difference, average, count, min/max, or ratio.
  • Use AiMe on unstructured or incomplete drafts that lack meaningful contract content.
  • Expect AiMe to red-line, edit, or compare clauses. Use Redline Agent or Search Agent for those tasks.
  • Ask AiMe to analyze multiple documents at once. AiMe works on one document at a time.
  • Ask AiMe to search extracted metadata. AiMe can only process the uploaded document.
  • Assume the output to be exhaustive or 100% accurate. You must review critical terms manually.
  • Expect AiMe to support non-English contract review unless Conga has confirmed the language to be supported.
  • Ask Copilot to review files that are larger than 12 MB or 200 pages.

Giving Feedback

Your feedback helps AiMe work better.

When AiMe returns an answer, you can assess the quality of its response using the thumbs-up/thumbs-down feedback icons. Clicking thumbs-up returns positive feedback to the AI engine. The assumptions it made to understand your prompt and generate the response are given more weight in the language model.

AiMe also interprets copying the results to the clipboard using the copy button () as a thumbs-up response.

Clicking thumbs-down indicates your dissatisfaction with the results. This negative feedback also informs the AI so that it can improve its responses. When you click the negative-feedback icon, a pop-up window appears, asking you to explain why you weren’t happy with the results.
Figure 1. Negative Feedback Pop-up
You can click any of the pre-set boxes and enter up to 255 characters of additional feedback in the text entry box.

AiMe’s AI engine uses your feedback to inform future responses.

Reviewing the AI Chat History

Recall recently asked questions.

All AI queries are logged. You can find out which types of question were asked about a document, when those questions were asked, and read the AI’s responses.
  1. To access your AI chat history, click the menu icon () and choose Chat History from the pop-up menu.
  2. The Chat History pop-up shows summary titles of questions pertaining to this document sorted by how recently they were asked. Depending on the configuration, you may see queries from today, yesterday, the past week, or the past month.
  3. To filter the questions by date, click the filter icon and select the section you will view. If the standard choices are not sufficiently granular, you can select Custom to raise a date picker and select or enter a custom date range.
  4. Click any of the listed question summaries to raise the selected question or prompt and AiMe’s response.
  5. Click the Close hypertext to close the Chat History feature.

Generating a Document Summary

AiMe Assistant can summarize contract documents, supporting documents, global documents, and others, making it easier to review lengthy contracts. Use AiMe's Summary feature to generate summaries efficiently.
Note: AiMe cannot accept for summary documents that are larger than 12 MB or 200 pages.
  1. Open a document.
  2. Click the Summary button () in AiMe's navigation bar.


The DOCUMENT SUMMARY window opens, showing two summary sections.
  • The Contract Summary section highlights the key points related to the document.
  • The Brief Summary section offers a concise overview of the document.

Reviewing a Document’s History

You can review the history of any fields ingested into the system (in a Ready for Review, Ready for Approval, or Complete status). The Review History contains details about which fields were changed, who changed them, how they changed them (by creating, updating, or deleting), when they changed the fields, and the contents of the field.

Use Case

During an external audit, a compliance officer must demonstrate that a vendor agreement’s payment terms were extracted accurately and approved by two separate reviewers. Opening Review History and exporting the time-stamped change log shows who extracted the value, who edited it, and who approved it, in a format acceptable to the auditor.

  1. From the home screen, click the name of an uploaded document.
  2. Click the Review History tab.
The document’s working history in Discovery Agent is displayed for review.