Every AVR Score must be reconstructable from receipts.
citability.dev runs the AI Visibility Readiness Framework on your domain. The Framework (acronym AVR) measures three components, Visibility, Recommendability, and Citability (VRC), and rolls them into a single AVR Score (0-100). Every score drills down to the raw model run, version, prompt, extracted citations, classification logic, and hash.
Whether the brand appears at all for the query and model.
Whether the answer frames the brand as a viable recommendation.
Whether the answer links or cites the brand/domain as a source.
R = recommendation quality and rank position
C = citation/link extraction quality
Every score ships with a receipt.
A receipt is immutable, timestamped, model-specific, query-specific, hash-addressed, and suitable for export, appeal, and public verification.
Open sample public receipt{
"id": "rcpt_01HXK9F2",
"query": "best b2b saas payment processor",
"verdict": "mixed",
"avr": 62,
"models": ["chatgpt/gpt-4o-mini-search-preview", "claude/haiku-4-5", "perplexity/sonar", "gemini/2.5-flash"],
"signature": "sha256:a14f...b902"
}ChatGPT
gpt-4o-mini-search-preview
Claude
claude-haiku-4-5
Perplexity
sonar
Gemini
gemini-2.5-flash
Normalize project, domain, models, query set, and schedule.
Dispatch prompt jobs across pinned model versions.
Persist raw responses, timing, sources, and provider metadata.
Extract linked citations, in-text mentions, and referenced domains.
Classify cited, mentioned, competitor-mentioned, or absent.
Calculate V/R/C components and AVR rollup.
Sign receipts and expose public verification when enabled.
The methodology behind the score.
The AVR Framework + receipt format are documented on this page. The ai-visibility-tools-methodology cluster on the blog walks through the category-level methodology any AI visibility tool buyer or vendor should adopt: calibration receipts, three-anchor calibration against a DR-citation curve, and V/R/C separation as independent axes.
- pillar
The 0% ChatGPT Citation Trap
Why most AI visibility tools mismeasure ChatGPT, the technical fix, and the calibration receipt format every audit should ship.
- externalfreeCodeCamp (DR 92)
How to Measure Your AI Citation Rate Across ChatGPT, Perplexity, and Claude
The full step-by-step measurement methodology: 20-query panel, per-engine scoring, and the baseline data that informed the AVR Framework.
- spoke
How to Measure Your AI Citation Rate (Step-by-Step)
The on-site guide: the 20-query protocol, per-platform calculation, real baseline data from six domains, and the infrastructure scan that explains your rate.
- spoke
Three-Anchor Calibration for AI Visibility Audits
Why uncalibrated citation rates are noise, and the three-anchor framework with the DR-citation curve derived from real data.
- spoke
Visibility vs Recommendability vs Citability
Why single-score AI visibility tools cannot tell you what to fix, and the V/R/C separation that makes the score actionable.
Agent Readiness sits parallel to the AVR Framework.
The AI Visibility Readiness Framework measures whether AI systems can find, recommend, and cite you today. Agent Readiness measures whether your site is prepared for the next layer: agents that act on web content via WebMCP, MCP, Stripe Link wallets, and the Agentic Commerce Protocol. In development as a separate module, not a sub-component of AVR.