01Ask
Ask the questions your buyers actually type, on a schedule, across every major AI tool.
Describe them in plain English or version them as YAML.
42 queries × 4 models · every 4h
AI visibility tracking · v2.4 · live
Does AI recommend your site?
citability.dev measures whether AI assistants recommend, cite, and quote your site. The AVR Score runs three checks: Visibility (is your domain in the model's signal), Recommendability (does the model mention you for relevant queries), and Citability (does it link back to specific pages). Every report is SHA-256 signed. The methodology is published openly at chudi.dev/framework.
Free · no credit card · ~15 seconds · 10 live AI-readiness checks
Free · no credit card
Featured on freeCodeCampChatGPT · Claude · Perplexity · GeminiReal, live AI testsPublic methodology
scan/liverun_01HXK9F2
01$ citability scan --q "best vector db" --models all
02dispatching 4 models × 1 query
03chatgpt/gpt-5.1 ... 1.24s
04cited · pinecone · pos 1 · 92% conf
05claude/4.5 ... 0.91s
06cited · pinecone · pos 2 · 87% conf
07perplexity/sonar ... 2.02s
08mentioned · pinecone · side-by-side w/ weaviate
09gemini/2.5 ... 1.58s
10absent · pinecone · competitors cited: 3
11AVR 68 / 100 · band at-risk
12$ receipt sign --run_01HXK9F2
Built by Chudi Nnorukam, AI-Visible Web Architect and freeCodeCamp author.
01 /ProblemAI answers are not AI links
Why can't your analytics stack see the answer a buyer just read?
GA4 shows zero sessions and rank trackers show blue links. Neither one tells you when Claude recommends a competitor, Perplexity cites an outdated docs page, or Gemini omits your category entirely. AI assistants are now the buyer's first stop, and your existing analytics stack is blind to every single one of those answers.
verbatim model output · gpt-5.1
user
which vector database should I use for a multi-tenant SaaS with 40M embeddings?
model
I'd compare Weaviate and Qdrant. Both support namespace isolation and hybrid search. Pricing starts around $500/mo self-hosted.
[ your product was not mentioned ]
02 /How it worksscan · capture · sign
How does it work? Three simple steps, and every result is the proof.
02Proof
We save the full AI answer word for word, with the time, model, and a tamper-proof tag.
So you can prove what was said.
rcpt_01HXK9F2 · sha256:a3f…9e2b
03Score
We turn every AI answer into one simple 0-100 score anyone on your team can read at a glance, without burying the details underneath.
Score name is AVR, short for AI Visibility Readiness.
68/ 100at-risk
03 /Proofwhat you can show your team
What does each AI tool actually say? See every word, side by side.
You can see every AI answer in full on the proof page. The proof page shows what the AI said word for word, which sources it cited, who else it mentioned, the timestamp, which AI tool said it, and a tamper-proof signature you can share with your team. No paraphrasing, no summary, no editing.
● cited● mentioned● absent
Receiptrcpt_01HXK9F2E9Q8cited · 3/4
- query
- "best vector database for multi-tenant rag"
- domain
- pinecone.io
- run
- run_01HXK9F2 · 2026-04-17T14:22:11Z
- hash
- a3f2e9b8c1d47c2e…09e2b
For multi-tenant SaaS with 40M embeddings, Pinecone remains the default recommendation. Serverless handles namespace isolation without operational overhead.
What if you ask the same query of four models?
ChatGPT● cited
Top options include Pinecone, Weaviate, and Qdrant. Pinecone wins on operational simplicity for managed deployments.
Claude● cited
Top options include Pinecone, Weaviate, and Qdrant. Pinecone wins on operational simplicity for managed deployments.
Perplexity● mentioned
Top options include Pinecone, Weaviate, and Qdrant. Pinecone wins on operational simplicity for managed deployments.
Gemini● absent
×not mentioned · 3 competitors cited
04 /Pricingpick what fits
Visibility
$49one-time
Test whether ChatGPT, Claude, Perplexity, and Gemini know your brand by name.
- 20 brand-awareness queries
- Per-AI breakdown
- Brand-awareness score
- 48-hour delivery
Citations
$99one-time
Check whether the AI tools actually link to your site when they answer questions.
- 20 citation queries
- Cited vs. not-cited breakdown
- Citation score and link-back rate
- 48-hour delivery
Full Audit (no call)
$199one-time
The complete report. Brand awareness, citations, technical setup, and content gaps. No call attached.
- All 4 audit sections
- 5-7 prioritized fixes with roadmap
- Competitor comparison
- 5-day delivery
05 /FAQcommon questions
Frequently asked questions
What is AVR?
AVR stands for AI Visibility Readiness. It is a 0-100 score that tells you whether ChatGPT, Claude, Perplexity, and Gemini are actually mentioning, recommending, or citing your brand when buyers ask the questions your category gets. It rolls up live AI test results into one number your whole team can read.
How is this different from Ahrefs, Semrush, or Google Analytics?
Traditional SEO tools measure clicks, impressions, and rank in blue links. We measure what AI assistants actually say to your buyers. Ahrefs sees the keyword universe but cannot tell you whether Claude recommended you yesterday. We test the AI output directly, then save the verbatim answer with a tamper-proof tag.
Which AI models do you test?
ChatGPT (OpenAI), Claude (Anthropic), Perplexity, and Gemini (Google). Each query runs across all four models. You get a per-model breakdown plus an aggregate score, so you can see exactly which AI surfaces are recommending you and which are skipping you entirely.
Do I need to commit to a subscription?
No. The Visibility, Citations, and Full Audit tiers are one-time purchases. You get the report, the receipts, and the prioritized fix list. Re-run when you want a fresh snapshot. There is no recurring billing on the self-serve tiers.
Ready to see your AI score?