Introduction

​

What is VectorLint?

VectorLint is a command-line tool that evaluates and scores documentation using large language models (LLMs). Instead of regex patterns that can only catch surface-level issues, VectorLint uses an LLM-as-a-Judge approach to catch terminology misuse, technical inaccuracies, and style inconsistencies that require contextual understanding to detect. If you can write a prompt for it, you can lint it with VectorLint.

​

Why VectorLint exists

Traditional prose linters like Vale work by matching text against fixed regex patterns and word lists. They catch what you explicitly tell them to catch — but they can’t reason about meaning, context, or technical accuracy. VectorLint fills that gap. You define a rule once as a Markdown prompt, and the LLM applies it across your entire content library — scoring each document, surfacing specific violations, and explaining why each violation matters. This gives documentation teams something they haven’t had before: a shared, measurable definition of content quality that scales across writers, repositories, and content types.

​

What you can check

​

How scoring works

VectorLint uses two scoring methods depending on the rule type: Density-based scoring is used for rules that count discrete violations (like a grammar checker). VectorLint calculates scores based on error density — errors per 100 words — so results are comparable across documents of any length. Rubric-based scoring is used for rules that measure quality on a spectrum (like tone or completeness). The LLM scores each criterion on a 1–4 scale, which VectorLint normalizes to a 1–10 scale for consistent reporting.

​

How false positives are reduced

VectorLint filters raw LLM candidates through a series of gate checks before surfacing violations to help keep its output precise:

1. Candidate generation — the LLM returns all potential violations, each with required gate-check fields: rule support, exact evidence, context support, plausible non-violation, and fix quality.
2. Deterministic filtering — VectorLint applies a strict filter and only surfaces violations that pass all required gates.

VectorLint’s output is intentionally stricter than raw model candidates; it reports only findings that pass all gates. You can tune how aggressively the pipeline filters findings to match your content workflow. See Tuning evaluation precision.

​

Next steps