# Pretence **Purpose** To investigate and learn about the role of genAI in gaming. **Core Game Systems & Supporting Systems** There are two core systems: NPCs (+ conversation) and Missions. The first is NPCs as generative agents. NPCs have short term conversational memory. They also have long term memory. This includes long term memory of their backstory as well as long term memory of whatever happens in the game. They also have access to game state knowledge that exists at game initialization and that evolves over time as the game state changes. NPCs reflect on conversations with the player as well as their experiences inside of the game. This allows the NPC to evolve based upon their conversations with the player as well as their experiences in the game. NPC prompt pipelines leverage both reasoning and emotional system to improve the quality of npc responses. The second is Missions. A mission is the system by which NPCs that have become companions (part of the player's party/group) are sent on missions. The NPCs interact with the world via these missions and the game state and world state are updated appropriately. **Game Designer Frontend** The game designer frontend is a web-based react (localhost) system for creating new worlds, new npcs, new missions, and game knowledge. **Game Frontend** A simple localhost web-based react frontend for playing your games. This is really just for testing systems. Like I guess it's a game technically, but it's not meant to look good as the purpose of this project is not to make a game. --- # Agent Instructions: 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: ``` GET https://pretence.gitbook.io/pretence/pretence.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.