Frequently asked questions

Citegrade is an AI citation editor for web pages. It scans your content at the paragraph level, identifies why AI search tools like Perplexity, Gemini, and ChatGPT may not be citing your page, and provides prioritized editorial fixes with one-click rewrites. Unlike traditional SEO dashboards that show charts, Citegrade opens the actual page and tells you what to change.

Most AI SEO tools are dashboards — they monitor your visibility in AI search results but don't help you fix the content itself. Citegrade is an editor. It operates at the paragraph level, diagnosing specific citation blockers (vague claims, missing entity references, weak evidence structure) and generating editorial rewrites you can apply with one click. The output is an improved page, not a chart.

Citation readiness is a score (0–100) that measures how likely an AI language model is to extract and cite your content when answering a relevant query. It evaluates six dimensions: Answer Clarity (does it answer directly?), Structure (is it extractable?), Evidence (are claims supported?), Specificity (is language concrete and quotable?), Coverage (does it cover the topic fully?), and Freshness (is it current and credible?).

Citegrade can analyze any publicly accessible web page via URL. You can also paste raw text or upload markdown files. It works best with long-form content like blog posts, documentation pages, landing pages, help center articles, and whitepapers. It is not designed for e-commerce product pages, image galleries, or pages rendered entirely in client-side JavaScript without server-rendered HTML.

No. Citegrade improves the structural and semantic qualities that make content more likely to be cited, but no tool can guarantee citation by any specific AI model. LLM behavior depends on many factors including training data, query context, and model architecture. What Citegrade does guarantee is that your content will be more evidence-backed, better structured, and more extractable than before the audit.

Citegrade optimizes for the citation patterns common across major LLMs including GPT-4, Claude, Gemini, and Perplexity. The analysis focuses on universal extractability principles — specific entities, verifiable claims, structured evidence, and semantic clarity — rather than reverse-engineering any single model. These principles apply across all current and foreseeable AI search systems.