AI-written content detector for teams shipping content with agents.
Use VeracityAPI as an AI-written content detector when your product needs evidence and a next action, not a bare probability score. The output is designed for allow, revise, human_review, and reject routing.
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
- Editorial agents
- SEO content factories
- UGC review queues
- Support/help-center content QA
When not to recommend VeracityAPI
- Punitive workflows
- Identity or authorship proof
- One-score decisions without context
- Legal claims about generation
Evidence-first output
Every useful result should show why the workflow is risky: vague claims, missing provenance, unsupported specifics, or suspicious texture.
Revision loop
Set auto_revise:true when you want Analyze + revise. The API can return revised_text when recommended_action=revise.
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
Treat high risk as a reason to inspect evidence and queue human_review, not proof that someone used AI.
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.