> For the complete documentation index, see [llms.txt](https://docs.airops.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.airops.com/insights/prompts/recommended-prompts.md). # Recommended prompts The **Recommended prompts** tab is an inbox of new prompts generated for your brand each week. Recommendations use your Brand Kit context and market data to reflect the topics, competitors, and audiences you care about. Review the queue to expand your coverage without researching every prompt manually. Accept prompts you want to track and decline the rest. ## Review recommended prompts ### Open the recommendations inbox Open **Insights → Prompts → Recommended prompts**. A badge on the tab shows the number of recommendations waiting for review. ### Evaluate a recommendation Each recommendation includes the following fields: | Field | Description | | --------------- | ----------------------------------------------------------------------- | | **Prompt** | The recommended question or prompt | | **Reasoning** | Why AirOps recommended the prompt, when available | | **Topic** | The topic associated with the prompt | | **Volume** | Relative search interest: Low, Medium, or High | | **Mentioned** | Whether answers to the prompt are likely to mention your brand | | **Cited** | Whether answers to the prompt are likely to cite your brand as a source | | **Competitors** | Competitor brands that tend to appear in answers | ### Accept or decline prompts Choose an action for each recommendation: * **Accept:** Add the prompt to [**Your prompts**](/insights/prompts/your-prompts.md) and begin tracking it across AI platforms. AirOps preserves its associated topic. * **Decline:** Remove the prompt from the recommendations inbox. Declined prompts do not resurface. * **Search:** Find a recommendation by keyword. ### Review prompts in bulk 1. Use the header checkbox to select every visible recommendation, or select individual rows. 2. Confirm the number of selected prompts in the footer. 3. Click **Accept all** or **Decline all**. Bulk acceptance respects your workspace's tracked prompt limit. AirOps notifies you when a selection would exceed the limit. ### Recommendation cadence AirOps adds recommendations for each Brand Kit every week. You do not need to start a refresh. Check the tab the following week when the inbox is empty. ### Region and language Recommendations use the region set in your Brand Kit. AirOps uses the United States when no region is set. The Brand Kit region controls which prompts AirOps recommends. Regions added under Insight Settings for Regional Tracking control where AirOps monitors accepted prompts. Recommendations use English by default. To use another language, open Prompt Insight Settings and select a preferred language. AirOps applies the change to new recommendations. ## Explore prompts on demand Prompt Explorer generates recommendations for a topic without waiting for the next weekly batch. ### Open Prompt Explorer From the **Your prompts** tab, click **Explore Prompts**. AirOps preserves an in-progress or completed exploration, so you can leave the page and return through the same button. ### Configure an exploration Complete the form: | Field | Description | | ----------------------- | ---------------------------------------------------------------------------- | | **Topic** | The topic to explore. Select an existing topic or create one | | **Custom instructions** | Optional guidance that shapes the recommendations | | **Prompts per topic** | The number of prompts to generate: 5, 10, 25, or 50 | | **Brand Kit** | The Brand Kit used for the exploration when your workspace has more than one | Click **Explore Prompts** to start the exploration. It runs in the background and shows progress until the results are ready. ### Write custom instructions Use custom instructions to refine the audience, intent, angle, tone, product focus, or subjects to avoid. Clear, specific guidance produces more focused results. For example: > Focus on mid-market SaaS companies evaluating vendors for the first time. Emphasize cost-benefit analysis and implementation effort. Avoid questions about enterprise-only features. > Target engineering leaders in late-stage evaluation. Prompts should reflect technical depth, integrations, and security posture. Leave the field blank to generate recommendations from the selected topic, your Brand Kit context, and market data. ### Review exploration results Prompt Explorer results use the same format as the recommendations inbox. Each result includes volume, mention and citation indicators, competitor context, and any available reasoning. You can: * Click **Accept** to add a prompt to [**Your prompts**](/insights/prompts/your-prompts.md) under the selected topic. * Click **Decline** to remove a prompt from the results. * Click **Accept all** or **Decline all** to process the batch. * Click **Explore More Prompts** to run another exploration with different settings. Accepted prompts begin tracking in **Your prompts**. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.airops.com/insights/prompts/recommended-prompts.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.