AI Writing Risk Indicators

Language-aware risk review.

Estimate AI-writing risk with English and Bulgarian rules, optional author baseline comparison, and OCR fallback for scan-heavy PDFs.

English + Bulgarian OCR fallback Subscores + aggregate Optional baseline
Assessment model

Separate indicators for structural regularity, formulaic framing, personal voice, and optional baseline drift.

No binary verdicts
The result is a risk-oriented writing signal, not proof of AI authorship.

Assessment details

-- Idle
Upload a document to generate language-aware risk indicators and optional baseline comparison.

Language detection

The current version applies separate phrase sets and thresholds for English and Bulgarian. Unsupported or mixed-language samples are flagged with lower confidence.

OCR fallback

When a PDF does not expose enough embedded text, the extractor can fall back to OCR so scan-heavy documents remain analyzable.

Optional baseline

You can attach a previous text from the same author to measure style drift without turning the tool into a hard authorship classifier.