Text check: written by a human or a machine

Send a text — the scenario measures the style metrics, three assistants examine it from different angles and return a verdict with the reasoning.

  • A verdict with reasoning, not "it feels like it"
  • Three different perspectives, including the counter-argument
  • Style metrics are measured, not guessed
  • The marker-word list keeps updating itself
Set it up for yourselfScriptera

How it works

  1. Starts when: When chat message received
  2. Then: Load Fingerprint List
  3. Then: Extract Stylometric Metrics
  4. Then: Agent Orchestrator
  5. Then: Agent 1 - The Scanner
  6. Then: Package Scanner Output
  7. Then: Agent 2 - Forensic Analyst
  8. Then: Package Analyst Output
  9. Then: Agent 3 - Devil's Advocate
  10. Then: Final Verdict
  11. Then: Format Chat Message
  12. Then: Send Final Report
  13. Starts when: Schedule Trigger
  14. Then: Check Existing Words
  15. Then: Format Existing List
  16. Then: Find New Words
  17. Then: Split into Rows
  18. Then: Save New Fingerprints
  19. Then: LLM - Generator
  20. Then: LLM - Devil's Advocate
  21. Then: LLM Scanner
  22. Then: LLM - Analyst

You can launch this integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios