Skip to main content

KYRA:Docs - Document Data Extraction V2 Now Available

KYRA:Docs — Document Data Extraction V2 brings the review of extracted entity data, data groups, and related parties into a single, unified task. Reviewers can now compare extracted information against the current entity record, understand the outcome assigned by KYRA:Docs, and record an explicit resolution before any changes are applied. This release replaces the legacy extraction experience with a more controlled, transparent, and auditable review process — supporting both standard and Maker-Checker journeys.

Key Details​

  • Unified Review Task: Entity data, data groups, and related-party hierarchy updates are reviewed in one place, replacing the previously fragmented experience.
  • Source Traceability: Every extracted value is supported by full traceability — including document reference, page number, and AI rationale — so reviewers always understand why a value was extracted.
  • Explicit Resolution: Reviewers must record a decision on every extracted item before the task can be completed. No changes are applied without an explicit resolution.
  • Flexible Reviewer Control: Extracted values can be accepted, rejected, edited, or replaced with a custom value before being committed to the record.
  • Improved Related-Party Handling: Reviewers can compare potentially matching records, correct extracted information, and control whether an existing record is retained, updated, or replaced.
  • Maker-Checker Support: Changes are written only after the Checker completes their review, with no data committed during the review stage.
  • Automatic Task Completion: Tasks with no eligible content to extract complete automatically, removing unnecessary steps.
  • Document Scope Controls: Extraction can be limited to documents uploaded in the current journey and to the latest document versions only.

Implications​

  • Ensures no extracted data is applied to the entity record without a deliberate reviewer decision, reducing the risk of unintended changes.
  • Provides full traceability from extraction through to resolution, supporting compliance and governance requirements.
  • Improves reviewer confidence through source evidence and AI rationale surfaced directly in the task.
  • Supports Maker-Checker workflows natively, enabling institutions to apply appropriate oversight controls to document-driven data updates.

Client Adoption Guidelines​

  1. Create a draft of the relevant journey, remove the legacy Document Data Extraction task, and add Document Data Extraction V2 to a journey containing Documents V2.
  2. Enable the required entity-data and related-party extraction settings on the new task, and disable the extraction settings on the document upload and related party task if applicable.
  3. For Maker-Checker journeys, link a separate Checker task in Journey Builder before publishing.
  4. Validate the configuration in a lower environment before enabling on production tenants.
  5. Review the detailed user guides available via the community portal for full configuration and workflow guidance.

User Guide References​