eReadable

Methodology

This page explains how readability is measured, how issue detection works, where AI rewrite helps, and when manual review is required before publishing.

How readability is measured

We combine formula-based signals and structural checks. Formula outputs provide directional estimates, while issue detection identifies actionable lines to rewrite.

What formulas are used

  • Flesch Reading Ease
  • Flesch-Kincaid Grade Level
  • Gunning Fog
  • SMOG

How issue detection works

Detection highlights long sentences, difficult words, passive voice risk, and hard-to-scan structure patterns. Suggestions are prioritized so teams can fix high-friction lines first.

Where AI rewrite helps

AI rewrite accelerates simplification and plain-English adaptation, especially for support content, onboarding copy, and dense policy summaries.

Limitations

Model outputs can improve readability but may require context checks for legal precision, regulated language, or internal policy nuances.

When manual review is required

Use manual review for legal commitments, policy exceptions, compliance wording, or any text where wording changes could alter enforceable meaning.

Recommended flow: start in Readability Checker, refine in Text Simplifier, then validate with domain review.

FAQ

eReadable uses multiple formulas including Flesch Reading Ease, Flesch-Kincaid, Gunning Fog, and SMOG for directional diagnostics.

It can if unmanaged. Binding legal language should always be reviewed by a qualified human after rewrite.

Formulas and rewrite models improve clarity but cannot fully validate legal, regulatory, or business context intent.