Facts

Case Strategy transforms your key document set into a structured fact chronology, to help you understand who did what and when. As part of fact extraction, facts are grouped and in some cases, higher-level facts are constructed to deliver a succinct chronology that minimizes fact duplicates.

Once extracted, you can view facts in a chronological list on the Facts tab. Extracted facts can also be used to create memos. To learn more, see Memos.

Before using AI-based capabilities, we recommend learning about how the AI components in Case Strategy work so that you can leverage the features effectively. For more information, see Generative AI considerations for Case Strategy.

Extract facts

You can extract facts using Case Strategy on a saved search using the matter-specific information you enter in the prompt criteria fields.

While completing the prompt criteria fields, you can save your progress as a draft, referred to as a Working Copy, by clicking the Save and Close button and then resume completing the fields at another time. Only one draft can be saved for fact extractions per user at a time. A user can only access a draft that they saved.

If you do not enter a Prompt Criteria Name, the draft is named Fact Chronology: Working Copy.

To extract facts using a saved search on the Matter Home tab:

1. Navigate to the Matter Home tab.
2. Click Extract Facts.
   If you previously saved a fact extraction draft, it automatically populates the prompt criteria fields. Otherwise, the most recent prompt criteria fields you used for extracting facts populate instead.

3. Select a Saved Search to specify which documents are used to extract facts. This field selection is not saved as part of your existing prompt criteria.
   To ensure high performance, there is a limit of 5,000 documents in a job at a time. To learn more, see Size limitations.
   You can run multiple jobs at once with up to 10,000 documents at a time in a workspace at no additional cost. If you run more than 10,000 documents at a time, there may be additional costs incurred.
4. Optionally, click on Existing Prompt Criteria and select a previously run set of prompt criteria from the drop-down menu to populate that data in the modal. To learn more, see Existing Prompt Criteria.
5. Edit or complete the fields in the modal. To learn more about the fields, see Prompt criteria below. For writing tips on prompt criteria, see General writing guidelines.
   Each field has an individual limit of 4,096 characters except for the Prompt Criteria Name field which has a limit of 256 characters.

6. Optionally, if you would like to save a draft of the prompt criteria and resume working on the fields later, click Save and Close.
7. Click Extract Facts.
   The fact extraction job begins and once it completes, the user who started the job receives an email with job completion details. To learn more, see Job email results.

Errored documents during fact extraction

If any documents error during fact extraction, your organization is not charged for them, and the errored documents do not count towards your organization's Case Strategy total document count. Documents can error for a number of reasons including that the extracted text is empty or too large. To learn more, see Size limitations.

If there are documents that error during fact extraction, the user that started fact extraction is notified via email and a saved search is created to help you track those documents. The saved search is named after the entered Prompt Criteria Name value. Only the user that started the job can access the saved search initially.

To make the saved search available to other users:

1. Navigate to the Documents tab.
2. Click on the Saved Searches icon in the browser.
3. Right-click on the system-generated saved search in the list and select Edit. The saved search is named after the Prompt Criteria Name value.
4. Click on the Owner drop-down menu and select Public.
5. Click Save & Search.
   The system-generated saved search is now accessible to other users in the workspace.

Prompt criteria

The prompt criteria in Case Strategy give the large language model (LLM) the broad context surrounding a matter. This includes an overview of the matter, people and entities involved, detail on the legal issues that facts must relate to, and any jargon or terms that might help in understanding the documents.

Most fields display information which can guide the voice and tone of what you write. Further description of the fields for extracting facts is provided below.

• Prompt Criteria Name—Enter a name for this version of the prompt criteria. The name should be unique between jobs, and will be filterable when you are navigating the list of facts.
• Saved Search—Select an option from the drop-down menu to determine which documents are used to extract facts. This field selection is not saved as part of your existing prompt criteria. To ensure high performance, there is a limit of 5,000 documents at a time. To learn more, see Size limitations.
• Existing Prompt Criteria—Select a previously used set of prompt criteria from the drop-down menu to load that data into the respective prompt criteria fields. The drop-down menu displays existing prompt criteria created by any user. Optionally, you can search for the name of the Existing Prompt Criteria. The banner at the top of the modal updates whenever you select Existing Prompt Criteria to help you track the source of populated fields.
  Prompt criteria that are used for extracting facts can be reused while creating a witness summary or deposition outline and vice versa. Since there are some fields that are unique to each capability, only fields that each modal has in common are populated.
• Index Saved Search for Assist—Enable to index the documents in the selected Saved Search so that they can be referenced in Assist. This field selection is not saved as part of your existing prompt criteria. To learn more, see Assist.
• Matter Overview—Enter a concise overview of the case. Include the names of the parties involved, the nature of the dispute, and other important case characteristics.
• What are you trying to prove?—Outline your side of the argument and what you are trying to achieve in the case. This helps Case Strategy judge each fact as helpful or harmful to your case.
• Issues—Enter a list of issues and their descriptions. Issues should be in the following format: Issue name: Description. The issues you enter are used by Case Strategy to determine whether a document contains relevant facts and are also used to tag the facts it creates.
• People and Aliases—Enter the names and aliases of key individuals in the case. Include their role and any other affiliations.
• Noteworthy Organizations—Enter the name of organizations and other relevant entities involved in the case. Highlight any key relationships between the entities or their notable characteristics.
• Additional Context—Enter any additional information that does not fit the other fields. This section is typically left blank.
• Document Summary Instructions—Describe your desired content, structure, and/or formatting for the document summary. If you leave this blank, the job will create readable summaries of the document, but content, structure, formatting and style are not explicitly prescribed.

aiR Fact fields

After fact extraction, a set of fields populate with information based on your selected documents. Case Strategy creates up to 9 facts per document and the AI looks for any information relevant to your prompt criteria.

The following fields populate on extracted facts:

• Primary Fact Date—denotes the date when the fact occurred, or the start date for an event that occurred between certain dates, including the time. If an appropriate date cannot be found in the extracted text, this field is left blank.
• Fact—a brief title for the fact.
• Description—a more detailed description of the fact.
• aiR Issues—displays the issues that Case Strategy associated with each fact. The issues used are from the info you provide in the Issues field on your prompt criteria.
• aiR Entities—displays the entities that Case Strategy associated with each fact. You do not have to mention people in the People and Aliases or Noteworthy Organizations field in order for them to be found and set in the aiR Entities field.
• Document Summary—displays an AI-generated synopsis of the document which this fact came from.
• Fact Documents—displays the control number for the document or documents which this fact came from. You can link a fact to more documents manually if you want, but note that document preview only displays the first document listed.
• Citation—the portion or portions of the document used to support each fact. If multiple excerpts were found, they are separated by record separator symbols. You can view the citation highlights on a document in the Document Preview panel. To learn more, see Citation highlights in the Document Preview panel.
• Fact Score—an AI-generated score for each fact on a 0-4 scale.
  • 4—Very important; the fact is crucial and has a strong impact on proving the user's case.
  • 3—Important; the fact has a significant impact and is very relevant to the case.
  • 2—Moderately important; the fact has some impact and is somewhat relevant.
  • 1—Slightly important; the fact has minimal impact but might still be somewhat relevant.
  • 0—Not important; the fact has no relevance to the case. This score is very rare, as Case Strategy usually only extracts facts that it deems relevant.
• Arguments for Fact Score—an AI-generated rationale for the Fact Score to help you understand the scores better.
• Helpful/Harmful—an AI-generated decision on whether a fact is helpful, harmful, or neutral towards your case. This designation is based on your input in the prompt criteria in the What are you trying to prove? field.
• Prompt Criteria Name—the name which you entered in the Extract Facts modal. This field has a character limit of 256 characters.
• aiR Fact ID—A unique string identifier generated during fact extraction. This ID can be used for overlaying information using Import jobs. It is also referenced by the Duplicate Group ID field and the aiR Sort ID field.

Fact extraction considerations

Fact extraction uses Generative AI to read the extracted text of the documents, describe the contents using a document summary, and to create and score the facts. We strongly recommend that you provide an appropriate amount of oversight by having an attorney working on the case review the facts and then confirm or correct their language as needed. For further information, see the Generative AI considerations in Case Strategy.

If the same facts occur in multiple documents, duplicate or overlapping facts can be extracted. Case Strategy tags duplicate facts to help reduce the clutter, but if you avoid including duplicate content in the documents selected for fact extraction, you can reduce their prevalence.

Running multiple fact extraction jobs on the same document can also result in duplication, as prior facts are never deleted. We recommend that you filter fact lists using the Prompt Criteria Name, or consider deleting old facts if you have made improvements to your prompt criteria.

Document Preview panel

The Document Preview panel is available from the Matter Home tab. You can use the Document Preview panel to view documents without having to open them in the Viewer. To learn more, see Document and item list navigation.

Citation highlights in the Document Preview panel

Citation highlights display in the Document preview panel so you can locate key information at a glance without leaving the Matter Home tab. Citation highlighting displays for all facts created after August 14, 2025. Some facts created prior to that date may not support highlighting. Citation highlights display in a light blue color.

General writing guidelines

For the prompt criteria in all of the setup tabs, we recommend:

• Write as if less is more. Instead of pasting in a long review protocol as-is, summarize where possible and include only key passages.
• Phrase things in a positive way when possible. Avoid negatives such as not statements and double negatives.
• Do not include explanations of the law.
• Do not give the LLM commands, such as, “you will review XX." Instead, simply describe the case.
• Use whatever writing format makes the most sense to a human reader. For example, bullet points might be useful for the People and Aliases field, but paragraphs might make sense in another field.
• The LLM understands widely used slang and abbreviations, but it does not necessarily know jargon or phrases that are specific to an organization.

Size limitations

Based on the limits of the underlying LLM, Case Strategy has size limits for the documents and prompts you submit.

The documents and prompt criteria have the following size limits:

• Each Extract Facts field has an individual limit of 4,096 characters except for the Prompt Criteria Name field which has a limit of 256 characters.
• Each document's extracted text must be between 0.05 - 600 KB. Documents that are outside this range will not have facts extracted because they do not meet the size limits of the LLM.
• Each document's extracted text, when combined with the prompt criteria, must be less than 120,000 tokens which roughly corresponds to word count but this can be inflated for documents that contain a lot of numbers or punctuation.
• To ensure high performance, there is a limit of 5,000 documents in a job at a time. To learn more, see Size limitations.
• You can run multiple jobs at once with up to 10,000 documents at a time in a workspace at no additional cost. If you run more than 10,000 documents at a time, there may be additional costs incurred.

Job email results

Once a fact extraction job concludes, an email with additional information is sent to the user that started it. Each potential result is described below:

Name Result	Description
Job completed successfully	The job ran successfully and no further action is needed.
Job completed with errors	The job ran successfully but errors occurred. Case Strategy creates a saved search with the errored documents in it. Using the saved search, you can rerun a new job to resolve those errors.
Job is still running	The job has not completed yet. An email is sent to the user every hour after the job begins running and no action is needed on the user's part until the job concludes.
Job has timed out	The job has not completed successfully in time. You can rerun the job.
Job has failed	The job has not completed successfully. The email contains instructions on how to delete the created facts so that you can remove them and rerun the job.

Facts tabs

Once you extract facts, you can review facts in a consolidated fact list designed to help streamline analysis, apply advanced filters to focus on details that may be most relevant, and visualize a generated chronology of events with the Timeline. You can also view issues, entities, and related documents from the Facts tab.

Facts tab

On this tab, you can review facts in a consolidated fact list designed to help streamline analysis, apply advanced filters to focus on details that may be most relevant, and visualize a generated chronology of events with the Timeline, based on extracted facts.

The Facts tab contains the following sections:

1. Fact list

2. Fact Detail card

3. Filter panel

4. Timeline

Fact list

The fact list displays each Primary and Primary Constructed fact that was identified and extracted along with the date that the fact occurred and its Fact Score. To learn more about fact extraction, see Extract facts.

You can identify certain fact types by the icon displayed on the left side of the fact. The following fact type icons display in the fact list:

Icon	Fact Type
	Corroborating fact
	Primary Constructed fact
	Duplicate fact
No icon	Primary fact

To filter facts based on a keyword search, enter search terms into the Search all facts textbox and press Enter on your keyboard.

To adjust how facts are sorted in the list, click on the Sort: drop-down menu and select a sort option.

To view more information about a fact, click on the fact in the list to expand the Fact Detail card. To learn more, see Fact Detail card.

Fact Detail card

To view additional information about a fact, click on it in the fact list. The Fact Detail card expands to display the fact info. This includes a more detailed description of the fact, citations used in fact extraction, the Fact Score and rationale behind it, and a summary of the relevant documents. You can also edit the fact fields in the card. To learn more, see Editing a fact.

If you view a Primary (Constructed) fact, the Issues, Entities, and Citations that display originate from the corroborating and duplicate facts used to construct the Primary (Constructed) fact. Fact Score, Fact Score Argument, and Helpful/Harmful fields are not populated for Primary (Constructed) fact in the Fact Detail card.

Document Control Numbers listed in the Citations and Documents sections are hyperlinked so that you can click and open them in the Document Preview panel which launches next to the Fact list and Fact Detail card. After clicking on a hyperlinked Control Number, the Document Preview panel displays and navigates you to the highlighted citation in the document that was used to extract the fact.

If there is more than one document in the Citations and Documents section, the Next and Previous options display at the top of the Document Preview panel. You can click on these options to navigate from one document to the next.

You can navigate from the Document Preview panel back to the Fact Detail card by clicking on the Fact link.

Editing a fact

While reviewing facts, you can edit a fact's fields from the Fact Detail card. The process for editing fact fields varies by field.

You can edit the Fact Name, Primary Fact Date, Fact Description, Fact Score, Arguments, and Helpful/Harmful fields. To edit any of these fields:

1. Click on the field you wish to edit.
2. Using your mouse and keyboard, edit the field as desired. If you are editing the Primary Fact Date, you can enter a date using your keyboard or the calendar to select the date and time.
3. Optionally, if you have unsaved edits that you would like to cancel without saving, press esc on your keyboard.
4. To save your edits, either click outside of the field with your mouse or press Enter on your keyboard.

You can edit the aiR Issues and aiR Entities fields to either remove issues or entities from a field or add new ones from the Fact Detail card.

To add an issue or entity value:

1. Click on the field you wish to edit.
2. Optionally, to add an existing value, you can click on the drop-down menu to display a list of field values.
   1. To filter the list, enter terms in the textbox and press Enter using your keyboard. The options in the list update as you type so that only matching values display in the drop-down menu.
   2. Select any values you wish to add to either the aiR Issues or aiR Entities field.
3. Optionally, to add a new value, click on the textbox and enter the name of the field you wish to add.
   1. Click on the + icon to add the issue or entity value to the field.
      
      The field is automatically updated with the value added.

To remove an issue or entity value:

1. Click on the field you wish to edit.
2. To remove a field that is initially visible in the list, you can click the X icon next to its name.
3. Alternatively, you can click on the drop-down menu to display a list of field values.
   1. To filter the list, enter terms in the textbox and press Enter using your keyboard. The options in the list update as you type so that only matching values display in the drop-down menu.
   2. Deselect any values you wish to remove from either the aiR Issues or aiR Entities field.
4. Optionally, if you have unsaved edits that you would like to cancel without saving, press esc on your keyboard.
5. To save your edits, either click outside of the field with your mouse or press Enter on your keyboard.

Filter panel

You can also filter the fact list using the Filter panel. Click on the Filter icon to expand the panel. Each section in the panel can be expanded or collapsed by by clicking on the name. You can filter using the following fields: Primary Fact Date, Helpful/Harmful, Fact Score, Issues, Entities, and Prompt Criteria.

To apply a Date filter to the fact list, select an option or by click on the From or To Date options and enter a date using your keyboard. After a filter is applied, the list updates to only display facts that occur during or overlap with the date range you selected.

For example, if you enter a date range of From: 01/01/2020 and To: 01/01/2025, any facts that occur during that time span display in the fact list, including a fact that started on 3/7/2018 and ended on 7/2/2027.

Timeline

You can view facts in chronological order using the Timeline. Each fact displays the date when it occurred, avatars with the initials of the entities involved with each fact, and any aiR issues associated with the fact.

To expand or collapse the Timeline section, click on the Timeline toggle.

You can click on a fact in the Timeline to expand the Fact Detail card and view additional information about the fact. To learn more, see Fact Detail card.

To pan the Timeline up or down, you can either scroll with your mouse wheel up or down or left-click in the Timeline and hold down on your mouse and drag the cursor up or down to pan in that direction.

To zoom the Timeline in or out, press and hold Control on your keyboard and scroll your mouse wheel up or down.

While viewing the Timeline, you can expand the size of the Timeline to get a broader view of the Fact Chronology. To expand the Timeline, click the Fullscreen Timeline icon.

To reduce the size of the Timeline, click the Exit Fullscreen icon.

There are four different modes you can choose from when viewing the Timeline. Each mode is described below.

Mode Name	Description
Default	Facts are displayed individually based on the date that they occurred.
Cluster	Facts are grouped based on the date that they occurred and the total number of facts are displayed instead of each one individually.
Group by Issues	Facts with the same issues are grouped together. If facts share the same issues but occurred on a different date, then they are indented differently to help you visually distinguish them. Facts that have no issues assigned display together at the bottom of the Timeline.
Group by Entities	Facts that involve the same entities are grouped together. If facts share the same entities but occurred on a different date, then they are indented differently to help you visually distinguish them.

Issues tab

You can view a list of issues with the number of facts, entities, and documents for each issue displayed on the Issues tab.

To view the facts, entities or documents associated with an issue, click on the desired issue.

You can then select either the Facts sub-tab, Entities sub-tab, or Documents sub-tab to view more information. To learn more, see Facts sub-tab, Entities sub-tab, and Documents sub-tab.

Facts sub-tab

The Facts sub-tab filters facts so that you only see the ones that are associated with the issue you selected on the Issues tab. From this sub-tab, you can access the Fact list, Fact Detail card, Filter panel, and Timeline which function the same way as on the Facts tab. To learn more, see Fact list, Fact Detail card, Filter panel, and Timeline.

Entities sub-tab

The Entities sub-tab displays a list of entities associated with the selected issue. To filter the entities based on a keyword search, enter search terms into the Search all Entities textbox, and press Enter on your keyboard.

Click on an entity to see any facts associated with both the selected entity and issue. The Fact list, Fact Detail card, Filter panel, and Timeline are all accessible for these facts. To learn more, see Fact list, Fact Detail card, Filter panel, and Timeline.

To go back to the Entities list, click the Back icon.

Documents sub-tab

The Documents sub-tab displays a list of documents associated with the selected issue as well as a summary of each document. Click on the document's Control Number to open it in the Document Preview panel.