> ## Documentation Index
> Fetch the complete documentation index at: https://docs.simplismart.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Platform Scope

> An overview of the key capabilities offered by the Simplismart platform

The SimpliSmart platform provides end-to-end AI model lifecycle management, covering inference, training, deployment, and monitoring. Users can choose between shared or private endpoints and also opt for BYOC (Bring Your Own Compute) deployments for greater control.

### **Core platform features**

<AccordionGroup>
  <Accordion title="Training" description="Train and fine-tune GenAI models with customizable parameters for optimization." icon="brain" />

  <Accordion title="Deployment" description="Deploy models effortlessly across different environments." icon="server" />

  <Accordion title="Monitoring" description="Track performance metrics, latency, and resource utilization." icon="chart-line" />
</AccordionGroup>

***

### Inference

Inference on our platform can be accomplished in several ways to suit your needs.

1. [Shared endpoints](/inference/shared-endpoint) for cost-effective, scalable performance.
2. [Dedicated endpoints](/inference/dedicated-endpoint) to leverage dedicated resources with higher reliability and performance.
3. [Bring your own compute (BYOC)](/inference/bring-your-own-compute) to utilize your existing infrastructure, providing full control and potentially lower costs.

***

| **Deployment** | **Dedicated Endpoint** | **Compute Resources** |      **Model**     |   **Model Suite**  |
| :------------: | :--------------------: | :-------------------: | :----------------: | :----------------: |
|     Shared     |           No           |      Simplismart      |     Simplismart    | Simplismart Server |
|     Private    |           Yes          |      Simplismart      | Simplismart /Yours | Simplismart Server |
|      BYOC      |           Yes          |         Yours         | Simplismart /Yours | Simplismart Server |
|     On-Prem    |           Yes          |         Yours         | Simplismart /Yours |     Your Server    |

***

### Explore these core platform capabilities to accelerate your AI journey

<CardGroup cols="3">
  <Card title="Training" icon="brain-circuit" href="/training-suite/introduction">
    Train a model and optimize performance
  </Card>

  <Card title="Benchmarking" icon="chart-mixed" href="/model-suite/deployments/benchmarking">
    Benchmark and evaluate your deployed models
  </Card>

  <Card title="Inference" icon="microchip" href="/inference/shared-endpoint">
    Invoke deployed models for inference
  </Card>
</CardGroup>

<CardGroup cols="2">
  <Card title="Playground" icon="flask" href="/get-started/playground/large-language-models">
    Try out all the models from the playground
  </Card>

  <Card title="Deployment" icon="server" href="/model-suite/deployments/creating-a-deployment">
    Deploy a model on a private infra or your own cloud
  </Card>
</CardGroup>