For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.
Guardrails
Protect LLM interactions with prompt guards that evaluate and filter requests and responses for harmful or policy-violating content.
Guardrails are security policies that inspect LLM requests and responses to detect and block harmful, policy-violating, or inappropriate content before it reaches the model or the user. You can apply prompt guards to the request phase, the response phase, or both.
To learn more about guardrails, see the following topic.
To set up guardrails, check out the following guides.
To track guardrails and content safety, see the following guide.
About guardrails
How agentgateway's content safety controls, such as PII detection and DLP, layer to guard LLM …
Regex filters
Match and redact prompt content with custom regex patterns or agentgateway's built-in PII detectors.
OpenAI moderation
Use the OpenAI Moderation API as a prompt guard to screen LLM traffic for harmful content.
AWS Bedrock Guardrails
Apply AWS Bedrock Guardrails to filter LLM requests and responses for policy-violating content.
Azure AI Content Safety
Apply Azure AI Content Safety to detect harmful content and jailbreak attempts in LLM requests and …
Google Model Armor
Apply Google Cloud Model Armor templates to sanitize LLM requests and responses.
Custom webhooks
Integrate custom webhook servers to configure advanced content safety requirements.
Multi-layered guardrails
Chain multiple prompt guards so each request passes every check in order, for defense in depth.
