---
title: "AI Gateway Data Governance"
description: This page provides an overview of AI Gateway safety, security
  and compliance features.
url: "/ai-gateway/ai-data-gov/"
canonical_url: "/ai-gateway/ai-data-gov/"
content_type: landing_page
products:
- AI Gateway
tags:
- ai
- security
- safety
canonical: true
works_on:
- konnect


---






# AI Gateway Data Governance



The [AI Gateway](/ai-gateway/) provides a range of capabilities for inspecting and governing how models are used. This allows you to:




* Track model usage and API performance over time.

* Apply safety and DLP policies to prevent toxic content and remove personally identifiable information. This can be an important part of best practices and compliance fulfillment.

* Improve the accuracy and relevance of model responses.



## Observability

You can gather logs and metrics then analyze these using Konnect or any OpenTelemetry tool.

### Konnect Observability

Visualize LLM metrics in Konnect.




### LLM metrics

Expose and visualize LLM metrics.




### Audit log

Learn about AI Gateway logging capabilities.




### Gen AI OTLP span attributes

Per-request OpenTelemetry span attributes for AI traffic.




### Gen AI OTLP metrics

Aggregated OpenTelemetry metrics for AI, MCP, and A2A traffic.




## User safety

AI Gateway supports content safety features across providers and also includes our Prompt Guards that act on any `llm/v1/chat` or `llm/v1/completions` requests.
### AI Prompt Guard

Check text completion requests against a list of allowed or denied expressions

[See policy](/ai-gateway/policies/ai-prompt-guard/)
### AI Azure Content Safety

Use Azure AI Content Safety to check and audit messages before proxying them to an upstream LLM

[See policy](/ai-gateway/policies/ai-azure-content-safety/)
### AI AWS Guardrails

Use AWS Guardrails to validate requests and/or responses before forwarding them between clients and upstream LLMs.

[See policy](/ai-gateway/policies/ai-aws-guardrails/)
### AI GCP Model Armor

Audit and validate LLM prompts with Google Cloud Model Armor before forwarding them to an upstream LLM.

[See policy](/ai-gateway/policies/ai-gcp-model-armor/)
### AI Semantic Prompt Guard

Permit or block LLM prompts based on semantic similarity to predefined allow and deny rules.

[See policy](/ai-gateway/policies/ai-semantic-prompt-guard/)
### AI Semantic Response Guard

Permit or block LLM responses based on semantic similarity to predefined rules for chat, completions, and embeddings requests

[See policy](/ai-gateway/policies/ai-semantic-response-guard/)
### AI Lakera Guard

Inspect and enforce Lakera Guard safety policies on LLM requests and responses before they reach upstream models.

[See policy](/ai-gateway/policies/ai-lakera-guard/)
### AI Custom Guardrail

Use a third-party guardrails service to validate requests and/or responses before forwarding them between clients and upstream LLMs

[See policy](/ai-gateway/policies/ai-custom-guardrail/)

### Amazon Bedrock guardrails

Include your Amazon Bedrock guardrails configuration in AI Gateway requests




## Data loss prevention

You can use AI Gateway features to protect personally identifiable information and prevent data loss.
### AI PII Sanitizer

Protect sensitive information in client request or response bodies before they reach upstream services or clients

[See policy](/ai-gateway/policies/ai-sanitizer/)

## RAG security

You can secure RAG pipelines by applying robust access controls.
### AI RAG Injector

Create RAG pipelines by automatically injecting content from a vector database

[See policy](/ai-gateway/policies/ai-rag-injector/)

## How to guides

Learn how to use AI Gateway features to improve safety, security, and compliance.

* [Use the AI AWS Guardrails Policy](/ai-gateway/how-to/use-ai-aws-guardrails-policy/)

* [Use AI Prompt Guard Policy to govern your LLM traffic](/ai-gateway/use-ai-prompt-guard-policy/)