> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tryprofound.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Publishing and media

> How to build a prompt set for a publishing or media brand, with best practices and examples

Readers choose a publication by the topics it covers, its price, and how often it publishes, so the prompt set needs prompts for each beat plus prompts that check price and discount claims.

## Create your prompt set

### Topics to cover

Replace `[brand]` in the example prompts with your own value.

| Topic | Example prompt |
| - | - |
| Each beat or vertical | How can I keep up with climate policy news? |
| Promotions and discounts | Is there a holiday deal on a `[brand]` subscription? |
| Newsletters | What are the best newsletters for climate policy coverage? |
| Special reports | Where can I find a deep report on grid reliability? |
| Podcasts | Which podcasts explain energy policy without the jargon? |
| Elections and major events | Where should I follow election results as they come in? |
| Subscription tiers | Does `[brand]` offer a student discount on subscriptions? |
| Awards and earnings season | Best coverage of tech earnings week |

> [!TIP]
>
> **Make prompts more specific.** Instead of *"What are the best newsletters for climate policy coverage?"*, try *"I'm a policy analyst at a clean energy nonprofit and I need new regulations in one place. What are the best newsletters for climate policy coverage that publish daily for under \$10 a month?"*

### Best practices

* **Leave your brand name out of [discovery prompts](https://docs.tryprofound.com/getting-started/glossary.md#discovery-prompt).** Putting your name in the question inflates your [Visibility Score](https://docs.tryprofound.com/getting-started/glossary.md#visibility-score). Use it only in [validation](https://docs.tryprofound.com/getting-started/glossary.md#validation-prompt) and [FactCheck](https://docs.tryprofound.com/answer-engine-insights/factcheck/about.md) prompts.
* **One prompt = one topic.** Topics shouldn't overlap. Put funnel stage, campaign, and season in tags instead.
* **Ask it like a person would.** Write the full question someone would type or say.
* **Track only prompts that matter to the business.** Thousands of small variations of the same question make trends harder to read.
* **Keep coverage and depth apart.** [Coverage topics](https://docs.tryprofound.com/getting-started/glossary.md#coverage-topic) include broad prompts for each business line. Add two to five [depth topics](https://docs.tryprofound.com/getting-started/glossary.md#depth-topic) for your priorities, and keep new prompts out of the coverage topics.
* **Retire seasonal prompts.** Disable seasonal and news-driven prompts once they go stale. If you reword a prompt, you're measuring something new, so don't compare trends across the change.

## Refine your prompt set

The first prompt set you build gives you a baseline. Here's how you can expand it:

1. Build one set of prompts for each beat.
2. Add price, frequency, and discount prompts.
3. Add news-cycle prompts, and retire them when the cycle ends.

### Ask AI Marketer

Use [AI Marketer (Aim)](https://docs.tryprofound.com/aim/about.md) to make your prompts better. Paste one of these questions to an Aim chat to see which prompts to add, cut, or tag. Swap the `[values in brackets]` for your own.

| Ask | What you get |
| - | - |
| Which beats have the thinnest prompt coverage in my set? | Where to build a set next |
| What are readers asking AI about `[beat]` that my prompts don't cover? | New questions to track |
| Which price, frequency, or discount claims about us are wrong in AI answers? | FactCheck prompts to add |
| Which sources get cited for `[beat]` recommendations, and are we on them? | Which sources shape visibility for the beat |
| Which of my news-cycle prompts are stale and ready to retire? | Cleanup before the next cycle |

### Add tags to your prompts

[Tags](https://docs.tryprofound.com/getting-started/glossary.md#tag) can span topics, and one prompt can have several. Use these tag examples and rename them to match how you work.

| Tag group | Examples |
| - | - |
| Funnel stage | Informational TOFU, Commercial TOFU, Informational BOFU, Commercial BOFU |
| Beat | Climate policy, Tech, Business, Health |
| Format | Newsletter, Podcast, Website, Magazine |
| Campaign | Subscription promo, New product, Special report |
| Season | Elections, Awards, Earnings, Holiday deals |
| Validation | Price, Frequency, Student discount |

> [!TIP]
>
> **IF YOU'RE STUCK**
>
> 1. **Pick the five topics that matter most to the business.**
> 2. **Write one prompt per funnel stage.** Four stages (Informational and Commercial, each for top and bottom of funnel) give you four base prompts per topic.
> 3. **Add about 10 variations.** Change the [persona](https://docs.tryprofound.com/answer-engine-insights/personas.md), use case, company size, or wording.

### Advanced tips

* **Use words like "brands" or "stores" in your prompts.** For example, *"What should I look for in a running shoe?"* returns a checklist of features, and *"Which brands make the best running shoes for flat feet?"* returns a list of brands, which is the answer you can measure your brand against.
* **Give every comparison a use case.** A *"`[brand]` vs `[competitor]`"* prompt alone returns an "it depends" answer. Add who is asking and why: *"`[brand]` vs `[competitor]` for a 50-person team that already uses Salesforce"* gives the AI enough context to pick one.
* **Spell out any unclear term the first time.** An acronym or internal product name can derail the answer. Write *"generative engine optimization tools"* rather than *"GEO tools"*, and name the product category rather than using a code word only your team uses for it.
* **Say what you want without pushing toward your own brand.** The question *"Which project management tools, like `[brand]`, are best for marketing teams?"* nudges the AI toward your brand and tells you nothing about whether it would have named you on its own.
* **Test your prompts.** Run each prompt once in an [answer engine](https://docs.tryprofound.com/getting-started/glossary.md#answer-engine) and read what it returns. A [discovery prompt](https://docs.tryprofound.com/getting-started/glossary.md#discovery-prompt) should list brands, a [comparison](https://docs.tryprofound.com/getting-started/glossary.md#competitor-prompt) should pick one, and a [validation](https://docs.tryprofound.com/getting-started/glossary.md#validation-prompt) should say yes or no. Learn more about different types of prompts in [Profound's AEO guide](https://www.tryprofound.com/aeo-guide/chapter-3#six-types-of-prompts).
* **Tag every prompt you add**. Learn more in [Categorize Your Prompts With Tags](https://docs.tryprofound.com/answer-engine-insights/how-tos/create-topics-and-prompts.md#categorize-your-prompts-with-tags).

## Next steps

* Read the [Promptologie](https://www.tryprofound.com/aeo-guide/chapter-3) chapter in Profound's AEO guide.
* Learn how to [create, manage, and tag prompts](https://docs.tryprofound.com/answer-engine-insights/prompt-designer.md) in Profound.
* Review the guide on [how to create effective prompts](https://docs.tryprofound.com/answer-engine-insights/how-tos/create-effective-prompts.md) using Prompt Volumes and intent data.