// runnable playbook

AI-generated content dispute

is this image / text / code AI-generated? content-provenance, model fingerprinting, prompt-history reconstruction.

a guided path, not automation — each step opens a tool you run yourself; nothing uploads. progress is saved only in this browser.

// based on the curated pipeline

wraps the AI content — provenance kit preset — drop disputed text + images → AI text fingerprint → image provenance → metadata scrubbing → pixel stego → report

methodology guide →worked example →full tool list →

guided steps

0/6 done

01
evidence manifest generator
hash every disputed artifact before analysis
open tool →methodology
your note (local only)
02
ai generated text fingerprint analyzer
statistical and structural hints of LLM-generated prose
open tool →methodology
your note (local only)
03
ai generated image provenance analyzer
generator / model fingerprint hints from image artifacts
open tool →methodology
your note (local only)
04
metadata scrubbing tool artifact detector
detect deliberate EXIF/XMP stripping — common when hiding AI origin
open tool →methodology
your note (local only)
05
image steganography detector
pixel-level stego analysis on any images in the dispute set
open tool →methodology
your note (local only)
06
case report generator
draft a report summarizing authenticity signals for mediation or litigation
suggested options · title: AI content — provenance assessment
open tool →methodology
your note (local only)

when you're done

export a run summary — a small JSON record of which steps you marked done, your notes, and a self-hash so the record can't be silently altered. it is your reproducibility note, not a per-tool receipt: each tool emits its own input→output receipt when you run it.