How the engine works

The prose engine is the system that grades your writing. Here is exactly how it works.

It is fully deterministic

The same text always produces the same scores. There is no randomness, no model inference, and no variation between runs. Submit the same passage twice and you get the same results both times.

There is no AI in grading

The engine uses published readability formulas and rule-based analysis. The formulas are:

• Flesch-Kincaid Reading Ease and Grade Level (Kincaid et al., 1975)
• Gunning Fog Index (Gunning, 1952)
• Coleman-Liau Index (Coleman and Liau, 1975)
• Brysbaert (2019) silent reading research for reading time estimates

These are the same formulas used in academic research, style guides, and readability tools for decades. Inkbreaker did not invent them. It applies them consistently, calibrates them per writing type, and shows you the results.

What happens to your text

Your text is processed server-side, on Inkbreaker’s own infrastructure. It is not sent to a language model. It is not used for training. The engine itself keeps no separate copy of it, and computing the metrics you asked for is the only thing it is used for. Your work is saved to your account, in your notebook and your submission history, because it is yours to come back to, and deleting it deletes it. There is more detail in Privacy and your writing.

No model touches the product

There is no AI anywhere in Inkbreaker, and that includes content moderation. Submissions are screened by deterministic, rule-based filters that run on Inkbreaker’s own servers, and anything they flag is queued for a person to review. No AI service is involved, and your writing is never sent to an external provider.

What the engine measures

• Readability: Reading Ease, FK Grade, Vocabulary Complexity, Reading Level (Coleman-Liau), Reading Time
• Structure: Average Sentence Length, Sentence Length Variation, Word Count, Sentence Count, Paragraph Count
• Vocabulary: Vocabulary Range, Lexical Density, Repetition Score
• Style: Passive Voice, Adverb Density, Dialogue Ratio, Syntactic Depth, Sentence Opening Variety

Each metric is computed from your text directly. There is no interpretation, inference, or opinion in the computation. What each metric means defines every one. The numbers are the numbers.

Where you can run it

You get a full report every time you submit an exercise. You can also grade any draft on its own from the Tools panel in the editor, without submitting anything. Both use the same engine and the same benchmarks, so the numbers match. Grading a draft in the editor does not change the piece and does not award XP. See The editor and notebook for how to open it.