> For the complete documentation index, see [llms.txt](https://cardstock-studio.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cardstock-studio.gitbook.io/docs/test/build-playtest-game.md).
# Build Playtest Game
{% hint style="success" %}
This is where an AI will literally code your game for the Cardstock Studio simulation engine. It uses all the rules, components, data, and game brief that you have built to complete an accurate simulation of your project.
Through simulations, you may find that there are edge cases that have been missed, or emergent behavior by the bots that do not reflect realistic human actions. You can come back to this page and refine the build at any time, without starting over.
{% endhint %}
## Start Here
Start by clicking the "*Export AI Instructions*" button, and passing the file to your AI, then "*Import*" the results.
The system will verify the input (not an AI process), to confirm validity.
## Initial Refinements
Once you submit the response, there may be **Questions & Flags**. Answer them in each text box, clicking "Add to Chat" for each.
This is a back-and-forth opportunity to ensure the game works as you intend. Green responses can sometimes be ignored — they are often simply the AI confirming a decision that they believe is probably correct.
Your responses populate the text box below, and clicking "*Export AI Instructions*" will include the responses with the AI prompt. As usual, feed the document to your AI and "*Import*" the response.
## Machine Validation Updates
There will most likely be one or more rounds of validation fixes. When the code is updated, the system auto validates, and provides issues, which you can "*Export AI Instructions"* to pass to your AI.
When the AI respond, "*Import*" the response to update the game code.
After one or more rounds, you should ind that the code is *Verified*, and you can move on to the next step.
## Future Refinements
At any time, you can describe a problem you're finding in your simulations in the text box, and then "*Export AI Instructions*" to fix the issue. Your description should be clear and precise using specific language to ensure the AI does not misunderstand.
---
# 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://cardstock-studio.gitbook.io/docs/test/build-playtest-game.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.
