# Best Practices for Building Agents Recap

## Fits into the LLM architecture

Sits between the application layer and the deployment layer to validate user prompts and model responses on two endpoints.

## Works with any LLM

Whether you’re using OpenAI or another large language model, Shield will be able to be integrated into the workflow.

## Provides real-time protection

Our inference deep dive capabilities allow us to detect and intercept any prompts that may potentially be considered harmful or elicit a potentially dangerous output.

## Arthur Shield is the key to deploying LLMs quickly and safely

### Sensitive Data Leakage

Protect your user’s data as well as your company’s proprietary data from being unintentionally leaked.

### Toxicity

Block LLM responses that are not value-aligned with your organization.

### Hallucinations

Detect likely incorrect or unsubstantiated responses from an LLM before they can cause harm to the end user.

### Prompt Injections

Identify and block attempts to override the intended behavior of an LLM by malicious users.

### Model Agnostic

We natively integrate GenAI and all key modalities, no matter if they're proprietary, commercial, or open-source.

### Platform Agnostic

Arthur Shield integrates with any leading cloud provider, from AWS to Azure, and beyond.

### Flexible Deployment

Our platform supports deployment across SaaS, managed cloud, and on-prem environment.

## See what Arthur can do for you.