---
title: "Detect privileged content"
method: POST
path: "/privilege/v1/detect"
tags: ["Privilege"]
---

# Detect privileged content

`POST /privilege/v1/detect`

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

Returns structured review flags with confidence scores and policy-friendly rationale suitable for discovery workflows and privilege logs. This endpoint is an AI-assisted triage tool and does not replace attorney judgment.

**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.

## Request body

- object
  - `content` string — Text content to analyze (required if document_id not provided)
  - `document_id` string — Vault object ID to analyze (required if content not provided)
  - `vault_id` string — Vault ID (required when using document_id)
  - `categories` string[] — Privilege categories to check. Defaults to all: attorney_client, work_product, common_interest
  - `jurisdiction` 'US-Federal' — Jurisdiction for privilege rules
  - `include_rationale` boolean — Include detailed rationale for each category
  - `model` string — LLM model to use for analysis

## Response `200`

Privilege analysis completed

- object
  - `privileged` boolean, required — Whether any privilege was detected
  - `confidence` number, required — Overall confidence score (0-1)
  - `categories` object[], required
    - `type` string — Privilege category
    - `detected` boolean — Whether this privilege type was detected
    - `confidence` number — Confidence for this category (0-1)
    - `rationale` string — Explanation of detection result
    - `indicators` string[] — Specific phrases or patterns found
  - `recommendation` 'withhold' | 'redact' | 'produce' | 'review', required — Recommended action for discovery
  - `policy_rationale` string, required — Policy-friendly explanation for privilege log

## Other responses

- `400` — Invalid request - missing content/document_id or content exceeds size limit
- `401` — Invalid API key
- `403` — API key does not have access to chat service
- `404` — Vault or document not found

---

[API](https://skmtc.net/casemark/apis/case-dev-api.md) · [All operations](https://skmtc.net/casemark/apis/case-dev-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/casemark/case-dev-api/revisions/5b7e64e6d6f9/schema)