Last date modified: 2026-Sep-17

Management

The Index Manager contains the list of indexes created in Assist or Case Strategy. An index is a set of documents that Assist searches to answer prompts. Each index is built from the extracted text of documents available in public saved searches within a workspace. Users can choose the index that best matches their prompt, or switch indexes to search for different topics or document sets in the same workspace.

Indexing and prompting do not incur additional costs.

Users responsible for managing indexes must be granted the Index Management permission to create, rebuild, and delete indexes. Individuals with Prompting permission may access the Index Manager list to select an index for their prompt. See Permissions for details on the Index Management and Prompting permissions.

ARM is not supported for Assist. Assist permissions, indexes, conversations, and metadata mapping cannot be archived, restored, or moved using ARM.

Suggested resources:

Indexes created in Case Strategy

A Case Home index can be created within Case Strategy as part of the facts generation process (shown below). It enables Assist to support case strategy development by leveraging the same document set used in Case Strategy analysis. See Creating a fact chronology for more information on this process.

Case Strategy's Generate Fact dialog with Index Saved Search for Assist option highlighted.

  • The Case Home index cannot be rebuilt or deleted from Index Manager because it is managed by the Case Strategy application.
  • Metadata mapping is not supported for the Case Home index. It is only supported for indexes created using Assist. See Metadata Mapping for more information.

Indexes created within Assist

Indexes can be created manually within Assist from public saved searches within the workspace.

  • Each index can include up to 300,000 documents.
  • A maximum of five (5) built indexes can exist at one time per workspace. This can be from a combination of the Case Home document set (Case Strategy) and public saved searches. See Working with indexes for details on adding and deleting indexes.
  • The indexes define the datasets from which Assist retrieves and generates answers.

Throughput expectations

  • Indexing speed varies by dataset size, document complexity, and available workspace resources. While typical cases are optimized, larger or complex datasets may take more time, possibly up to 6 hours, to finish with either a "Successfully build" or "Partially build" status.
  • Index creation is a background process that progresses automatically once initiated. While exact durations vary, it is recommended to allow sufficient processing time for workspaces containing large volumes of documents or complex extracted text.
Feedback