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

# Blog

## 19 September 2025

### Chloe Finally Has GPT Integration! 🚀

Big news for all Chloe users: **Chloe now comes with GPT integration**! This means smarter, faster, and more intuitive AI responses directly in your Discord server

{% columns %}
{% column %}

<figure><img src="/files/vZoZAuiv43eGUsDOxxrN" alt=""><figcaption></figcaption></figure>
{% endcolumn %}

{% column %}
Chloe now leverages **GPT integration** to provide smarter, context-aware responses in your Discord server. Whether it’s answering complex questions, assisting with Roblox Studio tasks, or moderating conversations, Chloe delivers fast and accurate AI-powered assistance tailored to your community.

**Key Benefits:**

* Understands context for more relevant answers 💡
* Adapts to your server’s style and needs 🎨
* Handles multiple tasks at once, saving time ⏱️
* Enhances community engagement with intelligent interactions 🌟

Experience a new level of AI support—Chloe doesn’t just respond, she understands.

{% endcolumn %}
{% endcolumns %}

<details>

<summary>Improved</summary>

* Context-Aware Answers
* Conversation history
* Fast response

</details>

***

## 11 November 2025

Hello everyone!\
As mentioned in a previous post, my team and I at **Polaris Integrations** are developing an AI chat-bot for Discord, built as a native integration (more commonly known as a “bot”). For those who want to catch up, you can find the initial announcement about *Chloe* here.

**What is Chloe**\
Chloe is a Large Language Model (LLM) based on OpenAI’s GPT technology. She is designed as a conversational assistant optimized for the Italian community on Discord.

**What “Powered by GPT” means**\
Saying that Chloe is *Powered by GPT* means that her intelligence is based on an OpenAI language model, while our team defines her behavior through a dedicated system file configured with various parameters, including:

* The AI’s name.
* Guidelines on how it should interact with users (for example: Chloe replies exclusively in Italian because she is meant for the Italian community).
* The AI’s purpose and manifesto.
* Creativity parameter (*temperature*). For Chloe, we set it to **0.3**, a value that prioritizes coherence and accuracy without removing creativity entirely. After extensive testing, this proved to be the best balance.

{% columns %}
{% column width="50%" %}

<figure><img src="/files/f3PnJYBAv64hFZxDQSQr" alt=""><figcaption></figcaption></figure>
{% endcolumn %}

{% column width="50%" %}

### **Infrastructure Challenges (AI Self-Hosted)**

To run a custom AI like Chloe, we use a dedicated VPS where the entire model is executed through Ollama, without relying on external API services. This gives us full control, but makes the infrastructure more challenging to manage.

### **Why is self-hosting complex?**

**More powerful and expensive servers**\
An LLM requires significant resources, so a powerful cloud server dedicated exclusively to the AI is needed.

**Model optimization**\
Configuring the model (quantization, parameters, behavior) requires continuous testing to maintain a good balance between quality and speed.

**Load management**\
A single VPS cannot handle unlimited requests; traffic and limits must be monitored to avoid slowdowns.

**Stability and maintenance**\
Updates, monitoring, restarts, and VPS security are essential to keep the AI online at all times.

**Conclusions**\
The Chloe project represents an important step for us in developing fully customized AI solutions optimized for the Italian community. Working on the self-hosted infrastructure, model configuration, and Discord integration allows us to build a tool that is truly ours—controllable, reliable, and adaptable over time.

{% endcolumn %}
{% endcolumns %}