Documentation

Everything you need to get oriented.

Start with the quickstart, then dig into how each metric is defined, how audits work, and what the allowance and trial mean for you.

Getting started

  • Introduction

    What Citeroot does today, what it deliberately doesn't, and how the pieces fit.

  • Quickstart

    From sign-up to your first baseline in about fifteen minutes.

  • Core concepts

    Projects, prompts, engines, runs, answers, sources and findings — the vocabulary used throughout Citeroot.

Measuring AI visibility

  • Metric definitions

    Exactly how named, cited, recommended, position, share of voice and the 95% interval are calculated — and where they can be wrong.

  • Prompt panels

    How to design, group and limit a prompt panel — and how to generate a starter set.

  • Source Map

    Read the sources behind your answers, how they're typed, and how gap lists work.

  • Reading changes and variance

    How Citeroot separates real movement from run-to-run noise.

  • Engines and models

    Which AI engines Citeroot asks, how, and how close an API answer is to what a person sees.

  • Runs and allowance

    How runs work, what counts toward your monthly answers, and how automatic cadence is chosen.

Diagnosing your site

  • Site Audit

    What the crawl checks, how domain verification works and how scores are reported.

  • Crawler access

    How Citeroot reports AI crawler permissions by purpose and what the statuses mean.

  • Briefs and insights

    Beta: drafts written from your own data, and how to treat them.

Export & roadmap

  • Exports and roadmap

    What you can take out of Citeroot today, and the integrations that are planned but not built.

Account & security