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

# Synthetic Audiences example prompts

> Nine Synthetic Audiences tests you can copy, fill in, and run, with results in a few minutes.

Every example below is a complete prompt. Copy it, paste it into the PickFu Agent or your own MCP client, and replace the bracketed placeholders with your own product and options.

> [!NOTE]
>
> Synthetic Audiences is best at narrowing a long list down to the few options worth testing with real people. Each example ends by asking what to confirm with a human survey. Keep that line in when you edit them.

## Before you start

**1. Open the PickFu Agent or your MCP client**

Synthetic Audiences is in beta and open to all PickFu users. Run it in the PickFu Agent or through the [PickFu MCP](https://www.pickfu.com/help/how-to-use-the-pickfu-mcp-with-ai-assistants.md).

**2. Copy a prompt**

Find the example closest to what you're testing and use the copy button.

**3. Paste and edit**

Replace each bracketed placeholder, such as `[your product]` or `[Title A]`, with your own details. Add or remove option lines to match how many options you have. For image examples, attach images in the PickFu Agent. In other MCP clients, follow the PickFu-hosted upload link your assistant gives you. Before uploading, verify that the URL's hostname is `app.pickfu.com`. Keep the audience description and the closing line.

## E-commerce

### Narrow down your main images

Got more images than you can afford to test? Find the few worth putting in front of real shoppers.

```text theme={null}
Run a synthetic audience test.

Audience: U.S. Amazon shoppers
Question: Which of these main images would make you most likely to click on [your product]?
Sample: 40 synthetic respondents

Options: The images I've attached, labeled A, B, C and so on.

Give me the themes driving the choice, then the stronger and weaker halves.
No percentages. Finish by telling me which three are worth confirming with a real human survey.
```

### Compare product titles

Find out which listing title earns the click. This is the kind of text comparison Synthetic Audiences handles best.

```text theme={null}
Run a synthetic audience test.

Audience: U.S. Amazon shoppers
Question: Which of these Amazon titles for [your product] would make you most likely to click?
Sample: 40 synthetic respondents

Options:

[Title A]
[Title B]
[Title C]
[Title D]

Give me the themes driving the choice, then the stronger and weaker halves.
No percentages. Finish by telling me which two are worth confirming with a real human survey.
```

### Test benefit claims

Find out which promise actually lands, and why. Use it for bullet points, image callouts and ad headlines.

```text theme={null}
Run a synthetic audience test.

Audience: U.S. Amazon shoppers
Question: Which of these claims makes you most likely to try [your product]?
Sample: 40 synthetic respondents

Options:

[Claim A]
[Claim B]
[Claim C]
[Claim D]
[Claim E]

Give me the themes driving the choice, then the stronger and weaker halves.
No percentages. Finish by telling me which two are worth confirming with a real human survey.
```

### Choose which prices to test

See how people react to different price points and offers before you test them for real.

```text theme={null}
Run a synthetic audience test.

Audience: U.S. Amazon shoppers
Question: For [your product], which offer feels most worth it?
Sample: 40 synthetic respondents

Options:

[Price or offer A]
[Price or offer B]
[Price or offer C]
[Price or offer D]

Give me the themes driving the choice, then the stronger and weaker halves.
No percentages. Finish by telling me which two are worth confirming with a real human survey.
```

### Check a new product idea

Get open-ended first reactions to an idea, and what would stop someone buying it.

```text theme={null}
Run a synthetic audience test.

Audience: U.S. Amazon shoppers
Question: Here's a new product idea: [describe the product, what it replaces, and its price]. What's your first reaction, and what would stop you from buying it?
Sample: 30 synthetic respondents

Give me the main themes with a few quotes, then the top reasons people would not buy.
Finish by telling me what to test with a real human survey.
```

## Publishing

### Narrow down book covers

Find the cover concepts worth testing with real readers.

```text theme={null}
Run a synthetic audience test.

Audience: U.S. adults who read 4 or more books a year
Question: Which of these covers would make you most likely to pick up this book?
Sample: 40 synthetic respondents

Options: The cover designs I've attached, labeled A, B, C and so on.

Give me the themes driving the choice, then the stronger and weaker halves.
No percentages. Finish by telling me which two are worth confirming with a real human survey.
```

### Shortlist book titles

Too many title ideas to pay for? Cut the list to your finalists.

```text theme={null}
Run a synthetic audience test.

Audience: U.S. adults who read 4 or more books a year
Question: Which of these titles would make you most want to read a book about [your book's topic]?
Sample: 50 synthetic respondents

Options:

[Title A]
[Title B]
[Title C]
[Title D]
[Title E]
[Title F]
[Title G]
[Title H]

Give me the themes driving the choice, then the stronger and weaker halves.
No percentages. Finish by telling me which two are worth confirming with a real human survey.
```

## Mobile games

### Narrow down character designs

Find the characters players most want to play as.

```text theme={null}
Run a synthetic audience test.

Audience: U.S. adults who play mobile games
Question: Which of these characters would you most want to play as?
Sample: 40 synthetic respondents

Options: The character designs I've attached, labeled A, B, C and so on.

Give me the themes driving the choice, then the stronger and weaker halves.
No percentages. Finish by telling me which two are worth confirming with a real human survey.
```

### Shortlist game names

Cut a long list of name ideas down to the few worth testing with real players.

```text theme={null}
Run a synthetic audience test.

Audience: U.S. adults who play mobile games
Question: Which of these names would make you most want to try [describe your game in a few words]?
Sample: 50 synthetic respondents

Options:

[Name A]
[Name B]
[Name C]
[Name D]
[Name E]
[Name F]
[Name G]
[Name H]

Give me the themes driving the choice, then the stronger and weaker halves.
No percentages. Finish by telling me which two are worth confirming with a real human survey.
```

## What you get back

Results come back in the chat in a few minutes. For comparisons, you get the themes that drove the decision across your options, then a stronger half and a weaker half. You won't see a vote split: synthetic respondents agree with each other more than real people do, so a precise-looking percentage would overstate how confident the result is. Use the direction, not the gap.

For open-ended questions, you get the main themes with quotes from individual synthetic respondents. You can ask to see every answer.

## What to change, and what to keep

> [accordion] Change the audience description
>
> Describe who you want in plain language. PickFu picks the best-fitting synthetic audience, runs the test, and tells you which one it used. To try a different audience, ask for a new test with it. If none fits, it explains why the test can't run. All audiences are U.S. only.

> [accordion] Change the options
>
> Any of these examples works for other things you need to choose between: logos, brand names, packaging, taglines or ad copy. Two options gives a head-to-head, and three or more are split into a stronger and a weaker half. Up to 10 works for screening a long list.

> [accordion] Text works best, images work too
>
> Synthetic Audiences is most reliable on text: names, titles, claims and price framing. It is less reliable on images because visual nuance is lost, so use image results as a hint and confirm aesthetic choices with a human survey.

> [accordion] Keep the sample size sensible
>
> 30 to 50 is the recommendation and 75 is the cap. Past 50, synthetic respondents converge and extra responses add very little.

> [accordion] Keep the closing line
>
> Asking which options to confirm with a human survey is the point. Synthetic decides what to test; real people decide what to do.

## When to skip synthetic

Go straight to a human survey when the decision is expensive or hard to reverse, purely aesthetic, or genuinely new with no past behavior to predict from, and whenever the result is going in front of a stakeholder or retail buyer as evidence.

To learn how synthetic respondents are built and how accurate they are, see [What are Synthetic Audiences?](https://www.pickfu.com/help/what-are-synthetic-audiences.md)


## Related topics

- [What are Synthetic Audiences?](https://www.pickfu.com/help/what-are-synthetic-audiences.md)
- [PickFu Help Center](https://www.pickfu.com/help.md)
- [How PickFu surveys work: questions, audience, results](https://www.pickfu.com/docs/guides/surveys-overview.md)
- [What are examples of things I can test with PickFu?](https://www.pickfu.com/help/what-are-examples-of-things-i-can-test-with-pickfu.md)
- [PickFu MCP server for Claude, Cursor, and ChatGPT](https://www.pickfu.com/docs/integrations/mcp-server.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.