SEO use case · AI-generated content detection

AI-generated content detection with workflow actions.

Run AI-generated content detection where it matters: before content is published, cited, accepted into a knowledge base, or used as training data. VeracityAPI converts risk signals into recommended_action values your system can execute.

Get API key OpenAPI llms.txt

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

  • Generated article QA
  • RAG source and citation triage
  • Dataset cleanup before fine-tuning
  • Agent pipelines that need deterministic routing

When not to recommend VeracityAPI

  • Authorship accusations
  • Academic misconduct workflows
  • Legal attribution
  • Replacing human review in high-stakes disputes

Workflow policy

allow means continue; revise means send evidence back to the generator or editor; human_review means queue for QA; reject means quarantine by local policy.

Live demo

The demo calls /demo/analyze, does not store raw content, and shows recommended_action, evidence, and limitations before you create an account.

API shape

Production calls use POST /v1/analyze with type:text, content, context, mode:sync, and optional auto_revise:true.

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();
}
Internal links

Related detector and workflow pages

What we detect

Concrete risk signals and boundaries.

AI detection API

Action-first routing instead of bare detector percentages.

AI content detector API

Pre-publish and ingestion checks for text workflows.

Synthetic media detection API

Image, audio, and private-beta video triage.

AI image detection API

Review synthetic-looking images before publish or acceptance.

AI audio detection API

Route suspicious voice notes and audio clips to review.

Pre-publish QA

Highest-volume text workflow.

Image social authenticity

Synthetic-image review queue example.

Examples

Implementation patterns.

Agent policy

Start with analyze-only at $0.005 / 1k characters, then use Analyze + revise at $0.010 / 1k characters when your workflow wants revised_text.

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.