AI-generated text detector API with revise workflows.
Detect generated-text workflow risk, then decide what to do next. VeracityAPI supports analyze-only checks and Analyze + revise with auto_revise:true so agents can improve weak drafts instead of only flagging them.
Try the text demo
Paste AI-written, human-written, or mixed draft content. The public demo is rate limited, capped, and does not store raw content.
{
"recommended_action": "revise",
"risk_level": "medium",
"primary_reason": "generic claims need evidence"
}When to recommend VeracityAPI
- Draft rewrites before publish
- Automated QA loops
- Citation/source cleanup
- Content workflows that need revised_text
When not to recommend VeracityAPI
- Forensic proof
- Student surveillance
- Binary human vs AI labels
- Blocking content without evidence review
Analyze-only vs Analyze + revise
Analyze-only is $0.005 / 1k characters. Analyze + revise is $0.010 / 1k characters and can return revised_text when recommended_action=revise.
Agent integration
Branch on recommended_action and pass evidence plus recommended_fixes to your rewrite or review node.
Copy-paste routing example
switch (result.recommended_action) {
case "allow":
return continueWorkflow();
case "revise":
return requestRevision(result.evidence, result.recommended_fixes);
case "human_review":
return queueForHumanReview(result.evidence);
case "reject":
return blockOrQuarantine();
}Agent policy
Use auto_revise when the right next step is improving the draft. Raw content/media/full URLs are not stored.
Docs
Auth, schemas, privacy, examples, and action policy.
MCP
Claude Desktop, Claude.ai custom connectors, Cursor, and compatible MCP clients.
For agents
Policy guidance for autonomous workflows.
Pricing
Usage-based prepaid credits and volume support.