Sign in
Privilege

Detect privileged content

Analyzes text or vault documents for legal privilege. Detects attorney-client privilege, work product doctrine, common interest privilege, and litigation hold materials.

Returns structured privilege flags with confidence scores and policy-friendly rationale suitable for discovery workflows and privilege logs.

Size Limit: Maximum 200,000 characters (larger documents rejected).

Permissions: Requires chat permission. When using document_id, also requires vault permission.

Note: When analyzing vault documents, results are automatically stored in the document's privilege_analysis metadata field.

post/privilege/v1/detect

Request body

contentstring

Text content to analyze (required if document_id not provided)

document_idstring

Vault object ID to analyze (required if content not provided)

vault_idstring

Vault ID (required when using document_id)

categoriesstring[]

Privilege categories to check. Defaults to all: attorney_client, work_product, common_interest, litigation_hold

jurisdiction'US-Federal'

Jurisdiction for privilege rules

include_rationaleboolean

Include detailed rationale for each category

modelstring

LLM model to use for analysis

Response

Privilege analysis completed

privilegedboolean required

Whether any privilege was detected

confidencenumber required

Overall confidence score (0-1)

recommendation'withhold' | 'redact' | 'produce' | 'review' required

Recommended action for discovery

policy_rationalestring required

Policy-friendly explanation for privilege log

Changes