Skip to main content
Gateway fact-checks LLM-generated text against your source documents. You provide a claim and sources, and Gateway tells you whether the claim is supported, refuted, or lacks sufficient evidence. 
from gateway import TextSource
from gateway.aws import AwsClient

client = AwsClient.from_sfn_arn("arn:aws:states:us-east-1:123456789:stateMachine:gateway")

ruling = client.judge(
    claim="The Eiffel Tower is in Paris and was built in 1889.",
    sources=[
        TextSource(id="doc1", text="The Eiffel Tower is located in Paris, France."),
        TextSource(id="doc2", text="It was completed in 1889."),
    ],
)

print(ruling.verdict)  # Verdict.SUPPORTS

​
How it works

  1. Claim decomposition - Gateway breaks your claim into individual statements
  2. Evidence retrieval - Each statement is matched against relevant passages in your sources
  3. Verdict classification - We determine whether each statement is supported, refuted, or lacks evidence

​
Supported clouds

Gateway deploys to your cloud account. We currently support AWS, with Azure coming soon. During onboarding, we provide the SDK and Terraform configuration for your cloud via SFTP.

​
Next steps

Deploy Gateway

Set up Gateway in your cloud account using Terraform.

Install the SDK

Install the Python SDK to interact with Gateway.