FAQ
Frequently asked questions.
Everything you need to know about VritantAI. Can't find an answer? Reach out to our team.
General
What is VritantAI?
VritantAI Discover is an AI visibility platform for e-commerce brands. It audits the structured data on your product pages, benchmarks how AI search engines mention your brand, and runs hallucination sweeps that flag AI answers contradicting your catalog.
Do I need a developer to set up VritantAI?
No. Discover starts from a product page URL. Connecting a store is optional and takes store credentials, not code. Every proposed change waits for your approval, and you apply approved changes yourself.
Which platforms are supported?
Discover can audit any public product page. Shopify and WooCommerce stores can be connected natively so checks run against your live catalog. Every change waits for your approval, and you apply approved changes in your store admin. Applying them to Shopify or WooCommerce from Discover is on the roadmap.
Is there a trial?
Not yet. Discover is in private beta; access is request-based and pricing is shared with accepted cohort members. The AI visibility check and the hallucination scanner are free to run without an account.
GEO & AI Visibility
Which AI providers does VritantAI benchmark?
VritantAI runs blind mention benchmarks across Perplexity Sonar, OpenAI API, Gemini API, Claude API, and DeepSeek API. Perplexity provides live-web evidence; the other configured APIs measure model-memory recall. Each provider is queried independently with no fallback chain.
How is the GEO score calculated?
The GEO score is a weighted composite: Schema Markup accounts for 50%, Page Performance for 30%, and Entity Coverage for 20%. Scores above 80 indicate strong structured-data health. Scores below 60 typically indicate critical missing structured data.
Will deploying a patch get my products cited by AI search?
Discover does not predict or guarantee rankings, citations, or traffic. AI engines re-crawl and re-index on their own schedules. Rerun a citation benchmark after your patches are live and compare it with your baseline to see what changed.
Can I reject a proposed GEO patch?
Yes. Every patch goes through a human-in-the-loop review queue. You can view the full diff, approve, reject (with an optional rejection note), or edit the patch before approving. Nothing is deployed without your explicit approval.
Hallucination Monitoring
How does hallucination monitoring work?
Scheduled sweeps ask the configured AI engines about your products, extract the factual claims in each answer, and compare them with your catalog. A claim that contradicts the catalog is logged with a severity of critical, warning, or info, and stays open until you resolve or dismiss it.
Can I check a page without creating an account?
Yes. The hallucination scanner checks one product URL, and the AI visibility check checks one website, both without an account.
Billing & Plans
Can I change my plan at any time?
Yes. An upgrade takes effect immediately. A downgrade or cancellation takes effect at the end of your current billing period, so you keep your current plan until then. Nothing is deleted when you move to a smaller plan: questions or locations over its limits are paused, not removed.
What happens if I go past my plan's limits?
Each Discover plan sets how many businesses, locations, questions and competitors you track, and which AI engines are measured. There is no overage charge: when a plan's monthly measurement budget is used up, sampling pauses until the next month and the dashboard shows the gap.
Which currencies do you bill in?
Discover is priced in USD and INR. Your billing currency is set at checkout from your billing country. INR prices exclude 18% GST.
Data & Privacy
Is my catalog data shared with other tenants?
No. All data is strictly isolated per tenant using PostgreSQL Row-Level Security (RLS). Every database query is automatically scoped to your tenant ID. Your catalog, audit history, and hallucination events are never accessible to other tenants.
Where is my data stored?
Data is stored in PostgreSQL via Supabase with pgvector for embeddings. Data at rest is encrypted. You can request data export or deletion at any time from your account settings.
Does VritantAI use my data to train AI models?
No. Your data is never used to train third-party AI models or shared with LLM providers for training purposes. LLM API calls use your data only as query context for the specific session and are not retained by the provider for training.