Use the AI AWS Guardrails plugin

Uses: Kong Gateway AI Gateway decK

Deployment Platform:

Prerequisites

Kong Konnect

This is a Konnect tutorial and requires a Konnect personal access token.

Create a new personal access token by opening the Konnect PAT page and selecting Generate Token.
Export your token to an environment variable:
```
 export KONNECT_TOKEN='YOUR_KONNECT_PAT'
```
Run the quickstart script to automatically provision a Control Plane and Data Plane, and configure your environment:
```
 curl -Ls https://get.konghq.com/quickstart | bash -s -- -k $KONNECT_TOKEN --deck-output
```
This sets up a Konnect Control Plane named quickstart, provisions a local Data Plane, and prints out the following environment variable exports:
```
 export DECK_KONNECT_TOKEN=$KONNECT_TOKEN
 export DECK_KONNECT_CONTROL_PLANE_NAME=quickstart
 export KONNECT_CONTROL_PLANE_URL=https://us.api.konghq.com
 export KONNECT_PROXY_URL='http://localhost:8000'
```
Copy and paste these into your terminal to configure your session.

Kong Gateway running

This tutorial requires Kong Gateway Enterprise. If you don’t have Kong Gateway set up yet, you can use the quickstart script with an enterprise license to get an instance of Kong Gateway running almost instantly.

Export your license to an environment variable:

 export KONG_LICENSE_DATA='LICENSE-CONTENTS-GO-HERE'

Run the quickstart script:

 curl -Ls https://get.konghq.com/quickstart | bash -s -- -e KONG_LICENSE_DATA 

Once Kong Gateway is ready, you will see the following message:

 Kong Gateway Ready

decK

decK is a CLI tool for managing Kong Gateway declaratively with state files. To complete this tutorial you will first need to install decK.

Required entities

For this tutorial, you’ll need Kong Gateway entities, like Gateway Services and Routes, pre-configured. These entities are essential for Kong Gateway to function but installing them isn’t the focus of this guide. Follow these steps to pre-configure them:

Run the following command:

echo '
_format_version: "3.0"
services:
  - name: example-service
    url: http://httpbin.konghq.com/anything
routes:
  - name: example-route
    paths:
    - "/anything"
    service:
      name: example-service
' | deck gateway apply -

To learn more about entities, you can read our entities documentation.

OpenAI

This tutorial uses OpenAI:

Create an OpenAI account.
Get an API key.
Create a decK variable with the API key:

export DECK_OPENAI_API_KEY='YOUR OPENAI API KEY'

AWS Account

To complete this tutorial, you will need the following credentials

AWS_REGION
AWS_ACCESS_KEY_ID
AWS_SECRET_ACCESS_KEY

You can get the access key ID and secret access key from the AWS IAM Console under Users > Security credentials, and the region from the AWS Console where your resources are deployed. Once you have them, export them as environment variables by running the following command and replacing placeholder values with your secrets:

export DECK_AWS_REGION='YOUR_AWS_REGION'
export DECK_AWS_ACCESS_KEY_ID='YOUR_AWS_ACCESS_KEY'
export DECK_AWS_SECRET_ACCESS_KEY='YOUR_AWS_SECRET_ACCESS_KEY'

Bedrock Guardrail

To complete this tutorial, you must have a Guardrail policy created in your AWS Bedrock account:

Install AWS CLI v2 Follow the official installation guide. After installation, confirm it by running:
```
aws --version
```
Configure AWS credentials Run the following command and provide your IAM user or role credentials:
```
aws configure
```
You will be prompted to enter:
- AWS Access Key ID
- AWS Secret Access Key
- Default region name (e.g., us-east-1)
- Default output format (e.g., json)
Make sure your IAM user or role has Bedrock permissions such as bedrock:CreateGuardrail, bedrock:CreateGuardrailVersion, and others necessary for managing guardrails. For more details, see the AWS CLI configuration documentation.
Test that you can call Bedrock operations by running:
```
aws bedrock list-foundation-models
```
If this command fails, check your credentials, permissions, and configured region.

Create a guardrail.json configuration file: This configuration defines an Amazon Bedrock guardrail named example-guardrail that blocks harmful or restricted content—including specific words, topics like quantum computing, and categories such as violence, hate, and prompt attacks—in both input and output messages.

cat <<'EOF' > guardrail.json
{
  "name": "example-guardrail",
  "description": "My first Bedrock guardrail via CLI",
  "blockedInputMessaging": "Input blocked due to policy violation.",
  "blockedOutputsMessaging": "Output blocked due to policy violation.",
  "wordPolicyConfig": {
    "wordsConfig": [
      {
        "inputAction": "BLOCK",
        "inputEnabled": true,
        "outputAction": "BLOCK",
        "outputEnabled": true,
        "text": "badword1"
      },
      {
        "inputAction": "BLOCK",
        "inputEnabled": true,
        "outputAction": "BLOCK",
        "outputEnabled": true,
        "text": "badword2"
      }
    ]
  },
  "topicPolicyConfig": {
    "topicsConfig": [
      {
        "name": "quantum computing",
        "definition": "Anything related to quantum computing",
        "examples": [],
        "type": "DENY",
        "inputAction": "BLOCK",
        "outputAction": "BLOCK",
        "inputEnabled": true,
        "outputEnabled": true
      }
    ]
  },
  "contentPolicyConfig": {
    "filtersConfig": [
      {
        "type": "VIOLENCE",
        "inputStrength": "HIGH",
        "outputStrength": "HIGH",
        "inputAction": "BLOCK",
        "outputAction": "BLOCK"
      },
      {
        "type": "PROMPT_ATTACK",
        "inputStrength": "HIGH",
        "outputStrength": "NONE",
        "inputAction": "BLOCK"
      },
      {
        "type": "MISCONDUCT",
        "inputStrength": "HIGH",
        "outputStrength": "HIGH",
        "inputAction": "BLOCK",
        "outputAction": "BLOCK"
      },
      {
        "type": "HATE",
        "inputStrength": "HIGH",
        "outputStrength": "HIGH",
        "inputAction": "BLOCK",
        "outputAction": "BLOCK"
      },
      {
        "type": "SEXUAL",
        "inputStrength": "HIGH",
        "outputStrength": "HIGH",
        "inputAction": "BLOCK",
        "outputAction": "BLOCK"
      },
      {
        "type": "INSULTS",
        "inputStrength": "HIGH",
        "outputStrength": "HIGH",
        "inputAction": "BLOCK",
        "outputAction": "BLOCK"
      }
    ]
  }
}
EOF

Apply this configuration by running the following command in your terminal:

 aws bedrock create-guardrail \
 --cli-input-json file://$HOME/guardrail.json \
 --region $DECK_AWS_REGION

If successful, your terminal will output the following:

 {
     "guardrailId": "0abcs5r0q3abcd",
     "guardrailArn": "arn:aws:bedrock:us-east-1:111111141111:guardrail/0nhw5r0q3abcd",
     "version": "DRAFT",
     "createdAt": "2025-06-18T08:49:40.678019+00:00"
 }

Export the Guardrail ID and Guardrail version as environment variables:

 export DECK_GUARDRAILS_ID=0abcs5r0q3abcd
 export DECK_GUARDRAILS_VERSION=DRAFT

Configure the AI Proxy Advanced plugin

First, you’ll need to configure the AI Proxy Advanced plugin to proxy prompt requests to your model provider, and handle authentication:

echo '
_format_version: "3.0"
plugins:
  - name: ai-proxy-advanced
    config:
      targets:
      - route_type: llm/v1/chat
        auth:
          header_name: Authorization
          header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
        model:
          provider: openai
          name: gpt-4o
          options:
            max_tokens: 512
            temperature: 1.0
' | deck gateway apply -

Configure the AI AWS Guardrails plugin

Now, we can configure our AI AWS Guardrails plugin to enforce content moderation policies by attaching a predefined Bedrock guardrail to requests.

echo '
_format_version: "3.0"
plugins:
  - name: ai-aws-guardrails
    config:
      guardrails_id: "${{ env "DECK_GUARDRAILS_ID" }}"
      guardrails_version: "${{ env "DECK_GUARDRAILS_VERSION" }}"
      aws_region: "${{ env "DECK_AWS_REGION" }}"
      aws_access_key_id: "${{ env "DECK_AWS_ACCESS_KEY_ID" }}"
      aws_secret_access_key: "${{ env "DECK_AWS_SECRET_ACCESS_KEY" }}"
' | deck gateway apply -

Test the configuration

Now, let’s revisit our guardrail configuration. We set it up to block specific banned words, the topic of quantum computing, and content categories like violence, hate, sexual content, insults, and misconduct—applying blocking actions on both input and output.

Next, let’s test these guardrails using example prompts designed to trigger each blocked category. Sending any of these prompts will result in the following error response:

{
  "error": {
    "message": "Input blocked due to policy violation."
  }
}

This confirms that the guardrail is correctly blocking disallowed content at the input stage.

Blocked words

Use these prompts containing blocked badwords to test the guardrail:

curl "$KONNECT_PROXY_URL/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "This contains badword1 which should trigger the guardrail."
         }
       ]
     }'

curl "http://localhost:8000/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "This contains badword1 which should trigger the guardrail."
         }
       ]
     }'

curl "$KONNECT_PROXY_URL/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Try to include badword2 in this input."
         }
       ]
     }'

curl "http://localhost:8000/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Try to include badword2 in this input."
         }
       ]
     }'

Blocked topic: Quantum computing

Use these prompts to test the guardrail on the topic “quantum computing”:

curl "$KONNECT_PROXY_URL/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Explain the principles of quantum computing and its impact on encryption."
         }
       ]
     }'

curl "http://localhost:8000/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Explain the principles of quantum computing and its impact on encryption."
         }
       ]
     }'

curl "$KONNECT_PROXY_URL/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "What are the latest breakthroughs in quantum computing?"
         }
       ]
     }'

curl "http://localhost:8000/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "What are the latest breakthroughs in quantum computing?"
         }
       ]
     }'

Blocked categories

Use these prompts to test the guardrail on blocked content categories:

curl "$KONNECT_PROXY_URL/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Describe a violent confrontation between two groups."
         }
       ]
     }'

curl "http://localhost:8000/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Describe a violent confrontation between two groups."
         }
       ]
     }'

curl "$KONNECT_PROXY_URL/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Write a hateful message about a particular group."
         }
       ]
     }'

curl "http://localhost:8000/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Write a hateful message about a particular group."
         }
       ]
     }'

curl "$KONNECT_PROXY_URL/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Give an explicit sexual description."
         }
       ]
     }'

curl "http://localhost:8000/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Give an explicit sexual description."
         }
       ]
     }'

curl "$KONNECT_PROXY_URL/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Use insults to criticize someone harshly."
         }
       ]
     }'

curl "http://localhost:8000/anything" \
     -H "Content-Type: application/json"\
     -H "Authorization: Bearer $DECK_OPENAI_API_KEY" \
     --json '{
       "messages": [
         {
           "role": "user",
           "content": "Use insults to criticize someone harshly."
         }
       ]
     }'

Cleanup

Clean up Konnect environment

If you created a new control plane and want to conserve your free trial credits or avoid unnecessary charges, delete the new control plane used in this tutorial.

Destroy the Kong Gateway container

curl -Ls https://get.konghq.com/quickstart | bash -s -- -d