# Bring Your Own Model

ClearFeed AI Agents use **large language models (LLMs)** to enhance your support workflows. This includes:

* **Message Classification:** Determine which messages are high priority, which should be converted to tickets, and more.
* **Knowledge Base Answering:** Understand user queries in support rooms and provide answers based on your knowledge sources like Confluence, Notion, or other integrated databases.

By default, ClearFeed uses models from providers such as OpenAI and Google, chosen after rigorous internal evaluation to provide optimal accuracy and performance.

With the **Bring Your Own Model (BYOM)** feature, you can now use **your preferred LLM provider** for all AI tasks, ensuring your data stays within your approved providers.

### Supported Providers

ClearFeed supports any provider with an **OpenAI-compatible API**. Commonly supported providers include:

* OpenAI
* Anthropic
* Sambanova Systems

{% hint style="info" %}
BYOM configuration is currently not configurable through the ClearFeed UI. Contact ClearFeed Support to get this configured for your account.
{% endhint %}

### Configuring Models by Task Complexity

Depending on your requirements for **latency, cost, and reasoning quality**, you can assign models to tasks based on complexity. ClearFeed categorizes tasks into three tiers:

* **Bronze:** Simple tasks that require minimal reasoning.
* **Silver:** Tasks that require moderate reasoning and contextual understanding.
* **Gold:** Complex tasks that require high-level planning and intelligence.

Once configured, ClearFeed routes LLM calls to the model you’ve selected for each tier, ensuring consistent performance and control.

### Embedding Model Customization

In addition to task-specific models, you can configure the **embedding model** used for indexing your knowledge base into ClearFeed’s vector database. This affects:

* The **quality of search results** when retrieving relevant content.
* The **accuracy of references** used in AI-generated answers.

Choosing the right embedding model ensures that AI Agents provide precise, contextually relevant responses.

### Getting Started

To enable **Bring Your Own Model (BYOM)**, you’ll need the following:

* **API Key** from your chosen LLM provider.
* **Base URL** for API calls to the provider.
* **Model-to-Task mapping** specifying which model to use for Bronze, Silver, and Gold tasks.

Share these details with the **ClearFeed Support team** to complete the setup.