Agents that transact: Introducing Amazon Bedrock AgentCore payments, built with Coinbase and Stripe

· Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Emerging Technologies & Innovation · Depth: Intermediate, medium

Summary

Amazon Web Services (AWS) has introduced Amazon Bedrock AgentCore payments (preview), a new feature enabling AI agents to instantly access and pay for resources like web content, APIs, and other agents. Developed in partnership with Coinbase and Stripe, this capability provides wallet infrastructure and payment rails for autonomous agents. AgentCore, already used by companies like Cox Automotive and Thomson Reuters, now allows agents to transact using the same identity, gateway, and observability systems. This marks the first managed, end-to-end payment solution for agents, covering wallet authentication, transaction execution, spending governance, and observability. The initial preview focuses on micropayments, supporting the x402 protocol for instant stablecoin transactions, with future plans for broader commerce flows.

Key takeaway

For CTOs and VP of Engineering evaluating AI agent development, Amazon Bedrock AgentCore payments simplify integrating transactional capabilities into agent workflows. This eliminates the need for bespoke billing relationships and complex orchestration, allowing your teams to focus on agent functionality rather than payment infrastructure. Consider piloting this preview to enable agents to dynamically access and pay for premium data, APIs, and services within defined spending limits, accelerating agent-driven commerce initiatives.

Key insights

AI agents can now autonomously transact for resources using integrated, managed payment capabilities.

Principles

Method

Developers connect an agent to a Coinbase or Stripe Privy wallet, register a funded source, and set session spending limits. AgentCore manages authentication, protocol negotiation, and transaction routing for paid resources.

In practice

Topics

Best for: CTO, VP of Engineering/Data, AI Architect, AI Engineer, Machine Learning Engineer, Director of AI/ML

Related on AIssential

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.