← Back to samples
Configuration Guide

Portfolio sample. Demonstrates configuration documentation for an enterprise healthcare platform. Fictional product; written to showcase technical writing methodology.

AI-Assisted Document Intake: Setup and Configuration

AI-Assisted Document Intake reads incoming faxed clinical documents, extracts structured data (member ID, diagnosis codes, requesting provider), and routes the request to the correct work queue. No manual data entry required for documents that meet the confidence threshold.

Prerequisites

Requirement Details
Feature License AI Document Intake license active on the tenant. Confirm in Admin > Licensing > Feature Entitlements.
Admin Role System Configuration Administrator role or custom role with INTAKE_AI_CONFIG permission.
OCR Engine Meridian OCR Engine 4.2+. Earlier versions do not support structured field extraction. Check in Admin > System > Component Versions.
Fax Integration At least one active inbound fax channel in Admin > Integrations > Fax Channels.
Work Queues Target queues must exist before routing rules can reference them.

Enable AI Intake by Request Type

AI Intake is toggled per request type. This supports phased rollout: enable for prior auth first, add concurrent review later.

  1. Go to Admin > Intake > AI Document Intake.

    The configuration page displays with a list of available request types.

  2. Locate the target request type. Click the toggle in the AI Intake column to On.

    Status changes to Enabled (Pending Configuration). The feature is not active until you configure an intake job.

  3. Repeat for each request type.

    Enabled types show a green indicator.

Disabling AI Intake for a request type does not delete existing configuration. Documents already processed retain their extracted data.

Configure the Intake Job

Each enabled request type needs an intake job defining which fields to extract and where to route results.

  1. Go to Admin > Intake > AI Document Intake. Click the request type name.

    The Intake Job Settings panel displays.

  2. In Extraction Fields, select the fields to extract:
    • Member ID (required)
    • Requesting Provider NPI
    • Primary Diagnosis Code
    • Service Type
    • Date of Service
    • Facility Name
  3. In Routing Rules, define queue assignments:
    1. Click Add Rule.
    2. Set the condition (e.g., Service Type = Inpatient).
    3. Select the target work queue.
    4. Click Save Rule.

    Rules evaluate top to bottom. First match wins. Documents matching no rule go to the default queue.

  4. In Default Queue, select the fallback queue.

    Required. The system will not process documents without a default queue set.

  5. Click Save Configuration.

    Status changes to Active. New documents on configured fax channels are now processed by the AI engine.

Confidence Thresholds

The engine assigns a confidence score (0 to 100) to each extracted value. Thresholds control what happens next.

  1. Go to Admin > Intake > AI Document Intake > Threshold Settings.

    The threshold page displays with sliders for each extraction field.

  2. For each field, set two values:
    • Auto-Accept: scores at or above this value are accepted without review. Default: 85.
    • Review Required: scores between this and Auto-Accept go to manual verification. Default: 60.

    Scores below Review Required are rejected. The field is left blank and the document is flagged for full manual intake.

  3. Click Save Thresholds.

    Applies to new documents only. Previously processed documents are not re-evaluated.

Start with Auto-Accept at 90+ during initial rollout. Lower it after reviewing accuracy data in Reports > AI Intake > Extraction Accuracy.

Troubleshooting

Documents stuck in "Processing" status

Cause: OCR Engine service unavailable or overloaded.

Fix: Go to Admin > System > Services. Confirm OCR Engine shows Running. If stopped, restart it. If Running but documents stuck 15+ minutes, check logs at Admin > System > Logs > OCR Engine for memory or timeout errors.

Low confidence on Member ID across all documents

Cause: Member ID format mismatch. System expects one format, incoming documents use another.

Fix: Go to Admin > Intake > AI Document Intake > Field Mapping. Verify the Member ID regex matches what providers actually submit. Common patterns:

Routing rules not assigning to expected queue

Cause: Rule order. First match wins. A broad rule above a specific rule captures everything.

Fix: Open the request type in Admin > Intake > AI Document Intake. Drag rules so specific conditions appear first. Use Test Routing to simulate a document and confirm the result.

Diagnosis codes not matching ICD-10 format

Cause: Engine extracted free-text descriptions instead of codes. Source document likely does not contain printed ICD-10 values.

Fix: Enable Diagnosis Code Lookup in Field Mapping > Primary Diagnosis Code. The system will match extracted text against the ICD-10 code set and return the best match. If no match meets threshold, the field goes to manual review.