> For the complete documentation index, see [llms.txt](https://pooky.gitbook.io/pooky/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://pooky.gitbook.io/pooky/core-gameplay/pookyball-gameplay/walkthrough-prediction-example.md).
# Walkthrough: Prediction example
**To make it clear, let’s walk through an example of a match in the French League between Paris and Marseille.**
It’s early January and the French League is starting to take shape. Paris and Marseille are tied at the top, separated only by goal difference. This is the biggest match of the season.
You (player A) and your friend (player B) gamify your club rivalry and go head-to-head in a prediction game.
### The predictions
#### Player A's Prediction
Player A predicts a tight game with Paris the eventual winner: \
**Paris \[1] - \[0] Marseille**
Player A uses the following Pookyball to make his prediction:
* Home Event: France
* City: Paris
* Season: current
* Pressure: 100%
* Rarity: Rare
#### Player B's Prediction
Player B is a lifelong Marseille fan. They know it will be difficult to win in Paris, but remain hopeful (the season is going well, after all). Player B predicts a low-scoring draw:\
**Paris \[1] - \[1] Marseille**
He uses the following Pookyball to make his prediction:
* Home Event: France
* Club Team: Lyon
* Season: Old 2021
* Pressure: 100%
* Rarity: Epic
### Game resolution
All the build up is warranted. The game is a low scoring match, but full of controversy and excitement. The final score is:
**Paris \[1] - \[0] Marseille**
Player A predicted the exact score. Player B didn’t predict the correct score, but still got the Defense prediction correct, so he will still score some points.
Let’s break down the Points each player won from their predictions and Pookyball.
{% hint style="info" %}
All Base values have the same expected value, except for Score, which is the only attribute that is not a yes/no question.
{% endhint %}
---
# 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://pooky.gitbook.io/pooky/core-gameplay/pookyball-gameplay/walkthrough-prediction-example.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.