# AI Agent NPCs

The NPCs in Hot Spring are emotionally responsive, context-aware characters designed to create continuity, personality, and interactive depth within simulation-based gameplay. These agents observe player behavior, store memory of past interactions, and adjust future responses based on accumulated context and in-game dynamics.

Each Agent is built with a set of behavioral components such as memory recall, mood-driven reactions, and personality variation. These features allow NPCs to evolve over time; reflecting the emotional cadence and decisions made by the user. A PET might become more attentive after repeated bonding rituals, or more hesitant if ignored for extended periods.

Every interaction is an opportunity to shape the dynamic between agent and player.

*<mark style="background-color:green;">Core features:</mark>*

* [x] **Dynamic memory trees**
* [x] **Mood-based behavioral shifts**
* [x] **Personality archetypes**
* [x] **Configurable interaction layers for both creators and players**

These NPCs appear across Simulation IP Games in different roles, including companions, task guides, quest givers, and ambient social actors. Dialogue, micro-interactions, and decision cues change based on both immediate context and longer-term relationship history. This enables a slow-burn emotional arc within gameplay that feels personal and persistent.

Internal configuration tools allow creators to define how agents behave, what emotions they express, and what memory thresholds trigger specific narrative or functional changes. The system prioritizes believability, growth, and interaction that supports long-form engagement.


---

# 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://docs.hotspring.games/the-cozy-world/ai-agent-npcs.md?ask=<question>
```

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.