> ## Documentation Index > Fetch the complete documentation index at: https://docs.oppin.ai/llms.txt > Use this file to discover all available pages before exploring further. # Hidden demand > Find the questions behind the questions. Prompts to paste into Claude or any assistant connected to Oppin. Paste a prompt into an assistant connected to Oppin ([how to connect](https://docs.oppin.ai/mcp/overview.md)) and replace the parts in \[brackets] with your own. In Oppin, the **MCP** tab of the **Data & MCP** page has the same prompts with your brand and a competitor already filled in. ## Quick questions One question, one answer. Paste it as it is. ### Which fan-out queries do we never show up in? *Quick question* The fan-out queries behind your questions where you never surfaced, most frequent first. ```text wrap theme={null} Using Oppin, which fan-out queries do we never show up in? ``` ### What are people starting to ask AI about in our category? *Quick question* The fan-out queries AI ran for the first time this month or more often than last month, and whether you show up in them. ```text wrap theme={null} Using Oppin, what are people starting to ask AI about in our category? ``` ## Workflows A few steps and one useful result. ### Hidden questions to new prompts *Workflow · Interactive page (treemap) + questions added on approval* Track the questions buyers really need answered, not just the ones you guessed. ```text wrap theme={null} Using Oppin, show the fan-out queries behind our tracked questions as a treemap: grouped by theme, sized by how often AI runs them, colored by whether we show up. Then propose up to 10 new questions to track for the biggest gaps, written the way a buyer would ask. Check they fit our plan, and don't add anything until I approve. ``` * **You get:** A map where the big uncovered blocks are the gaps, 10 proposed questions with a reason each, and the ones you approve added. * **Why it helps:** Fan-out queries show demand before it shows up in the answer. Distinctly Oppin. * **Changes tracking:** needs a connection with write access. The assistant shows the changes and waits for your yes. ### Buying-journey map *Workflow · Insight chart (journey strip)* See which stages of the buying journey you show up in, and where you drop out. ```text wrap theme={null} Using Oppin, map the fan-out queries behind our questions onto the buying journey: learning about the problem, comparing options, looking for alternatives, checking price, ready to buy. Draw it as a strip of stages, each showing how often we show up and who shows up instead. ``` * **You get:** A journey strip where the stage you drop out of is obvious, the leading rival at each stage, and the stage to fix first. * **Why it helps:** "We're strong on how-to, invisible once people compare" is a content plan in one line. * **Note:** Intents are matched on English wording. For a non-English brand, the assistant sorts the fan-out queries by reading them, so treat the stages as approximate. ### New market entry *Workflow · Answer (the question list) + questions added on approval* Get a baseline in a new country before the team spends there. ```text wrap theme={null} Using Oppin, we're expanding to [Mexico and Brazil]. Take our 15 best-performing questions and write local versions in [Spanish / Portuguese] for those countries, the way people there would ask, not word-for-word translations. Use the assistants that can search from those countries. Tag them "[market] expansion". Show me the list first. ``` * **You get:** Local versions of your best questions for each new country, on assistants that can search from there, tagged so the new market reads as its own report. * **Why it helps:** "What does AI say about us in Mexico before we launch there?" is a board-level question, and it needs a baseline taken before the spend. * **Changes tracking:** needs a connection with write access. The assistant shows the changes and waits for your yes. * **Note:** An assistant that can't search from a country is left out with the reason, never run from somewhere else. For now the new questions carry your brand's language label in exports and filters; the answers are unaffected, since the country is what localizes them. * **Take it further:** see [Markets a rival owns](https://docs.oppin.ai/mcp/use-cases/competition.md#markets-a-rival-owns) and [Where in the world are we strongest and weakest?](https://docs.oppin.ai/mcp/use-cases/pulse.md#where-in-the-world-are-we-strongest-and-weakest). ### Search Console to prompt candidates *Workflow · Ranked list + questions added on approval* Turn Search Console queries you don't track yet into new questions. ```text wrap theme={null} Using Oppin and Search Console, find question-style searches that bring us impressions but that we don't track in Oppin. Propose the 10 most promising as new tracked questions and add the ones I approve. ``` * **Why it helps:** Tracking reflects real demand, not guesses. * **Needs:** Search Console, connected in your assistant. * **Changes tracking:** needs a connection with write access. The assistant shows the changes and waits for your yes. ### Sales calls to tracked questions *Workflow · Ranked list + questions added on approval* Track the questions prospects actually ask, in their own words. ```text wrap theme={null} Using Oppin and [Gong / HubSpot / our call notes], pull the questions prospects asked in the last 30 days of sales calls. Group the recurring ones, drop what we already track, and propose the 10 most common as tracked questions, in the prospect's own words. Add the ones I approve, tagged "from sales". ``` * **You get:** The 10 most common prospect questions you don't track yet, with how often each came up. The ones you approve are added and tagged. * **Why it helps:** Real buyer language replaces marketing language in the prompt set, and sales gets a reason to care about Oppin. * **Needs:** Gong, HubSpot or call notes, connected in your assistant. * **Changes tracking:** needs a connection with write access. The assistant shows the changes and waits for your yes. * **Note:** Support tickets work the same way: use Zendesk or Intercom, ask for the questions someone who isn't a customer yet would ask AI about those problems, and tag them "problem-aware". * **Take it further:** see [Search Console to prompt candidates](https://docs.oppin.ai/mcp/use-cases/hidden-demand.md#search-console-to-prompt-candidates) and [Hidden questions to new prompts](https://docs.oppin.ai/mcp/use-cases/hidden-demand.md#hidden-questions-to-new-prompts). ## Agent tasks Longer tasks: the assistant investigates and reasons before it writes anything up. ### Category intelligence report *Agent · Deliverable (a research brief) · For agencies · For sales* How AI understands your category, written as a research brief. ```text wrap theme={null} Using Oppin, describe how AI assistants understand our category: the leading brands and why they lead, the main themes and questions, the fan-out queries, the sites it trusts, where assistants disagree, and where AI seems uncertain or inconsistent. Write it as a research brief for someone new to the category. ``` * **You get:** A category brief, useful for onboarding, strategy and new-business pitches. * **Why it helps:** Oppin data seen as market research, not just brand monitoring. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.