> For the complete documentation index, see [llms.txt](https://polypoll.gitbook.io/polypoll-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://polypoll.gitbook.io/polypoll-docs/user-guide/creating-markets.md).

# Creating Markets

Anyone with a paper account can create markets.

## What you set in the create flow

* question
* market type
* close date
* opening odds
* description
* cover image
* category and topics
* liquidity

## Binary vs multi-choice

### Yes / No

Use this for a clean binary outcome.

### Multiple choice

Use this when exactly one option should win.

The advanced control for adding answers after launch is hidden in the paper UI because most users do not need it.

## AI helpers

The paper creator supports:

* **Generate with AI** for resolution criteria and background
* **Generate AI answers** for multiple-choice options
* topic suggestions
* image lookup from Perplexity-backed search

The description format is designed to read like a high-quality consumer prediction market:

* **Resolution criteria**
* **Background**
* **This description was generated by AI.**

## Market images

You can:

* upload an image file
* paste an image URL
* ask AI to find one

Uploads support larger mobile images, including HEIC / HEIF formats.

## Creator rewards

When you publish a market:

* you get a **100 POLL** creator bonus

If the market attracts trading:

* 20% of the trade fee pool accrues to you
* that creator fee pool is paid when the market resolves

## Good market-writing rules

Write questions that are:

* objective
* time-bounded
* easy to verify
* precise enough to resolve cleanly

Bad title:

* `Will Iran launch a nuke?`

Better title:

* `Will Iran detonate a nuclear weapon before December 31, 2028?`

AI can help clean up titles like this, but the final wording still matters.


---

# 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://polypoll.gitbook.io/polypoll-docs/user-guide/creating-markets.md?ask=<question>&goal=<endgoal>
```

`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.