Human review handles ambiguous cases where DeepMod's confidence falls below your policy threshold. This section explains how to enable and use human review in your policies.

When Human Review Triggers

Human review automatically activates when three conditions are met:

1. Policy Review Mode: Your policy is set to "Human Review" mode

2. Ambiguous Result: AI confidence falls below your confidence threshold

3. Live Moderation: Only production runs trigger review (test runs are excluded)

When these conditions are met, the moderation run status becomes "Pending Review" instead of completing automatically.

Review Interface

What Reviewers See

Content: The original text exactly as submitted for moderation

AI Analysis:

• Which rules triggered ambiguous results

• Confidence scores for each rule

• Specific text segments that contributed to rule triggers

Decision Options:

• Approve (Success) or Reject (Failure)

• Required notes field for explaining the decision

Making Review Decisions

Reviewers evaluate the content against your policy rules and make a final decision. The human decision overrides the original ambiguous result.

Review Process

1. Automatic Queue: Ambiguous results enter the review queue

2. Access Reviews: Team members access pending reviews through the dashboard

3. Make Decision: Reviewer approves or rejects with explanatory notes

4. Complete: Final decision replaces ambiguous result and triggers webhook delivery

After Review Completion

Webhook Delivery: Completed reviews trigger webhooks with the final result, including:

• reviewed: true to indicate human review was completed

• reviewNote containing the reviewer's explanation

• Final decision (Success or Failure)

Audit Trail: All review decisions are permanently recorded with reviewer identity, timestamp, and notes.

Usage Tracking: Reviews are tracked in analytics but don't count toward usage limits since they update existing moderation runs.

Review Mode Settings

Human Review Mode: Ambiguous cases wait for human decision before completing

• Content evaluation pauses until reviewed

• Webhooks are delayed until review is finished

• Requires dedicated reviewers

No Review Mode: All decisions are automated

• Ambiguous results are sent via webhook for you to handle

• Faster processing with full automation

• No review capacity needed

Choose review mode based on your accuracy requirements and available review team capacity.

What's Next

• Policy Authoring Best Practices - Design policies that balance automation with review needs

• Plan Usage & Limits - Monitor review usage within your plan limits

Questions about human review? Contact support for guidance on setting up review workflows for your team.