RESEARCH · PROMPT EXPLORER & BRAND LOOKUP
Ask the question your buyer asks AI, then compare the answers.
Try a prompt in ChatGPT, then compare Claude, Gemini and Perplexity answers with the sources they cite. Look up how AI search cites any brand or domain before deciding what to track.
- 4 models side by side
- Sources for every answer
- Any brand or domain
- ChatGPTNames you · cites 3 sourcesYour /phones/ page cited
- GeminiNames youNo link to your site
- ClaudeDoes not name youCites 2 competitor pages
- PerplexityNames you · cites 5 sourcesYour blog post cited
4 models
ChatGPT, Claude, Gemini and Perplexity
Citations
the sources each answer links to
Brand lookup
mentions of any brand or domain
Track
move good prompts into tracking
INSIDE THE PRODUCT
Research AI answers before you track them.
Explore a question, read real answers and their sources, and keep the prompts worth watching.
Compare
Compare answers across models
Run one prompt in ChatGPT, or add Claude, Gemini and Perplexity, and read each answer with its available citations instead of relying on a single score.
- One prompt, several models
- Full answer text
- Available citations
| Model | Names you | Sources |
|---|---|---|
| ChatGPT | Yes | 3 |
| Gemini | Yes | 2 |
| Claude | No | 2 |
| Perplexity | Yes | 5 |
Brand lookup
See how AI search cites any brand
Look up a brand name or domain to see total mentions in ChatGPT and Google AI Overviews, sample prompts where it appears and the pages cited alongside it.
- Total mentions
- Sample prompts
- Pages cited alongside
Track
Track the questions that matter
Save the prompts worth watching under topics in Prompt Tracking, with the engines, market and schedule you choose.
- Save to a topic
- Choose engines and market
- Schedule checks
- Promptbest phone shop in nairobiWeekly · ChatGPT, Gemini
- Promptwhere to buy redmi note 14Weekly · ChatGPT, Gemini
- Promptis buying phones online safeMonthly · all engines
Share of voice
See who AI answers favour in your category
Brand lookup shows share of voice: how often a brand is mentioned compared with others in the same answers, with sample prompts and cited pages behind each number.
- Mentions compared across brands
- Sample prompts per brand
- Cited pages alongside
WHAT IT MEASURES
What an exploration shows.
What each metric tells you, and where it comes from.
| Metric | What it tells you | Source |
|---|---|---|
| Answer | The full answer each model returned for the prompt. | Model APIs |
| Citations | The sources each answer linked, where the model provides them. | Model APIs |
| Brand mentions | How often a brand or domain appears in sampled AI answers. | Brand lookup |
| Share of voice | A brand’s share of mentions among brands in the same answers. | Brand lookup |
| Cited pages | Pages cited alongside a brand. | Brand lookup |
UNDER THE HOOD
How Prompt Explorer and brand lookup work.
How the numbers are produced, so you can judge them for yourself.
One prompt, several models
Your prompt goes unchanged to each selected model API, and each answer is shown in full with the citations the model provides.
Cached answers reused
Answers already collected for the same prompt can be reused; uncached answers are paid provider requests, with the cost shown.
Brand lookup from samples
Brand lookup reads a sample of AI Overview and ChatGPT answers that mention a brand or domain, with sample prompts and cited pages.
Share of voice among brands
Share of voice compares how often each brand is mentioned among the brands in the same sample of answers.
HOW IT WORKS
From one question to a tracked prompt.
Four steps from connecting your data to a decision you can stand behind.
Ask the question
Start from your brand, a competitor or a buyer question.
Compare models
Read each model’s answer and citations side by side.
Look up brands
See how often a brand is mentioned and which pages are cited with it.
Track it
Save the prompts worth watching to Prompt Tracking with engines and a schedule.
WITH YOUR AI AGENT
Ask what AI says about you, right now.
Your agent can explore one prompt across models and save it for tracking.
- Uses the same data as the web app
- Paid tools estimate their cost first
- Saves the report to the project
YouWhat do AI models recommend for “best phone under 20000 in Kenya”?
explore_promptsave_ai_visibility_tracker
AgentThree models recommend Phone A and Phone B; two cite review-site.example. None mention yourstore.co.ke, although your guide covers both phones.
YouTrack that prompt weekly in all engines.
AgentThe tracker is ready with five engines on a weekly schedule; the monthly estimate is shown before you confirm.
Illustration · sample data
USE CASES
Built for the way you work.
How teams put it to work.
Check before you invest
See what AI answers say today before building content to change it.
Show a client the AI view
Compare models for a client’s key questions and the sources they trust.
Check the story AI tells
See how models describe your brand and competitors before a campaign.
Find the sources to beat
Read which pages models cite for your topic, and improve yours.
ALSO INCLUDED
More for AI research.
More capabilities that come with it, in the same project.
Ask from your agent
Agents can explore a prompt through MCP; it defaults to ChatGPT.
AI crawlers
Check AI crawlers actually fetch the pages you want cited.
AI referrals
See the visits AI assistants send, in GA4.
DATA & LIMITS
Know what the numbers can and cannot tell you.
Where the data comes from, how fresh it is, and the questions it cannot answer on its own.
| Source | What it provides | Freshness & limits |
|---|---|---|
| Model APIs | Answers and citations from ChatGPT, Claude, Gemini and Perplexity models. | Uncached answers are paid; API answers can differ from apps. |
| Brand lookup | Mentions in ChatGPT and Google AI Overviews samples. | Paid lookup; a sample. |
One answer is one sample
Models answer differently each time. Track prompts to see a trend.
APIs are not apps
Consumer apps can add memory, location and other context.
Absent is not never
A brand missing from a sample can still appear elsewhere.
Paid when uncached
New answers and lookups use provider credits; the cost is shown.
WORKS WITH
Connected to the tools you already use.
The sources and clients this feature reads from or works alongside.
CHOOSE THE RIGHT VIEW
Which view answers which question.
Start where the question points. Each view keeps its own source.
| Your question | Start with | Why |
|---|---|---|
| What would AI answer now? | Prompt Explorer | One prompt, several models. |
| Is my AI visibility improving? | AI search visibility | Tracked prompts over time. |
| Do AI crawlers fetch my pages? | Crawl Analytics | Verified requests in your logs. |
LEARN & TRY
Guides and free tools for the same job.
Read how the evidence works, or try a free check before you connect a project.
Mentions, citations and visits
Three AI signals that answer different questions.
Answer passage analyzer
Check a passage AI could quote.
FAQ
Prompt Explorer: common questions.
Straight answers about what it does, what it costs and where its limits are.
Are these the same answers people see?
Explorer answers come from model APIs and can differ from consumer apps. Prompt Tracking collects ChatGPT and Gemini from their consumer sites.
Does exploring cost credits?
Uncached answers and brand lookups are paid provider requests and are charged at actual usage.
Which platforms does brand lookup cover?
ChatGPT and Google AI Overviews.
Is a missing mention proof AI never names a brand?
No. Answers vary between runs, and a brand missing from a sample can still appear elsewhere.
Which models can I compare?
ChatGPT, Claude, Gemini and Perplexity models through their APIs.
Can I look up a competitor?
Yes. Brand lookup works for any brand name or domain.
Is share of voice the same as visibility?
No. It compares mentions among brands in sampled answers. Tracking shows your own mentions and citations over time.
Can my agent explore prompts?
Yes. Agents can explore a prompt across models and save it for tracking.
Are answers saved?
Explored answers are kept for reuse; to follow a prompt over time, save it to Prompt Tracking.
What are the limits of the data?
Explorer answers come from model APIs and can differ from consumer apps. Uncached answers and lookups are paid provider requests. A brand missing from a sample is not proof it is never mentioned.
How do I get access?
Platform access is reviewed. Request access with your website and the data sources you use, and the team will help you connect them.
See it with your own data.
Tell us about your website. We will review access and help you connect the right sources.