{
  "id": 4888870,
  "title": "How t54 built a trust layer with Amazon Bedrock AgentCore payments",
  "url": "https://urgent.news/2026/09/01/how-t54-built-a-trust-layer-with-amazon-bedrock-agentcore-payments",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-01T15:50:00.000Z",
  "source": {
    "name": "AWS Machine Learning",
    "slug": "aws-machine-learning",
    "url": "https://aws.amazon.com/blogs/machine-learning/how-t54-built-a-trust-layer-with-amazon-bedrock-agentcore-payments/"
  },
  "original_language": "en",
  "account": "t54 has developed a trust layer for Amazon Bedrock AgentCore payments, enabling AI agents to autonomously pay third-party services without human intervention. This trust layer, called x402-secure, scores endpoints and payment addresses in real-time using five independent signals, such as blockchain history, webpage legitimacy, social media footprint, API health status, and an aggregate risk score. The trust layer ensures that only safe services are paid for by agents.\n\nThe trust layer works in conjunction with Amazon Bedrock AgentCore payments, which handles spending limits, credential vaulting, and multi-provider support. These components work together to provide secure, scalable, and provider-agnostic payments for agentic systems. For example, a financial services team using an agentic system to monitor stock portfolios can now pay for real-time market data from paid APIs without manual approval for each transaction.",
  "summary": "t54 built x402-secure, a trust layer on Amazon Bedrock AgentCore payments that scores every endpoint before an autonomous agent pays it. See how session budgets, credential isolation, and a deterministic trust gate have governed more than 20 million agent-initiated transactions with no human in the loop.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "AWS Machine Learning",
        "title": "Build multi-tenant agentic chat applications on enterprise data with Amazon Bedrock Managed Knowledge Base",
        "url": "https://urgent.news/2026/08/31/build-multi-tenant-agentic-chat-applications-on-enterprise-data-with",
        "published": "2026-08-31T18:56:12.000Z"
      }
    ]
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}