AWS Innovations Q&A: Bedrock Agent Payments, Agent Toolkit, and More (May 2026)
Welcome to our latest Q&A covering the most exciting AWS announcements from last week. We dive into Amazon Bedrock AgentCore's groundbreaking managed payment capabilities for AI agents, the new Agent Toolkit for AWS, and other updates including EC2 instances and Valkey's second birthday. Let's explore these innovations in a conversational format.
1. What is Amazon Bedrock AgentCore's new payment capability?
Amazon Bedrock AgentCore has previewed the first managed payment system that lets AI agents autonomously access and pay for APIs, MCP servers, web content, and other agents. Developed in partnership with Coinbase and Stripe, it eliminates the need for developers to build custom billing, credential management, and compliance systems. You connect a Coinbase CDP wallet or a Stripe Privy wallet as a payment connection, set session-level spending limits, and your agent handles transactions autonomously during execution. The potential is huge, for example, a research agent could pay for real-time market data on the fly, or a coding agent could call paid APIs mid-task without human intervention. This capability positions AWS as a leader in enabling autonomous agent economies. To learn more, read the official blog post or check out the documentation, and get started with the AgentCore CLI.
2. What is the Agent Toolkit for AWS and how does it benefit developers?
The Agent Toolkit for AWS is a production-ready suite of tools and guidance, available at no additional charge, that helps AI coding agents build on AWS with fewer errors, lower token costs, and enterprise-grade security controls. It is the successor to the MCP servers, plugins, and skills previously available on AWS Labs. By using this toolkit, developers can reduce the friction of integrating AI agents with AWS services, streamline workflows, and maintain compliance. The toolkit includes pre-built skills and plugins hosted on GitHub, along with a quick start guide for easy onboarding. It's designed to accelerate development while ensuring robust security and cost efficiency. To begin, visit the quick start guide or browse the available skills and plugins on GitHub.
3. What is the AWS MCP Server GA and how does it relate to the Agent Toolkit?
The AWS MCP Server (Managed Model Context Protocol) is now generally available. It provides a managed remote MCP server that gives AI agents and coding assistants secure, authenticated access to all AWS services through a small, fixed set of tools. As part of the Agent Toolkit for AWS, it simplifies how agents interact with AWS resources, reducing the overhead of managing custom integrations. Developers can leverage this server to build more reliable and secure agent workflows. For a detailed technical overview, explore Seb Stormacq's blog post.
4. How can Amazon WorkSpaces for AI agents help organizations automate workflows?
Amazon WorkSpaces for AI agents (in preview) allows AI agents to securely access and operate desktop applications through managed WorkSpaces environments. This capability enables organizations to automate everyday workflows at scale while maintaining full enterprise-grade governance and compliance. For instance, an AI agent could remotely log into a virtual desktop, run specific software, perform repetitive tasks, and then log out—all without human supervision. This is particularly valuable for industries like finance, healthcare, and customer service where strict compliance and security are paramount. To learn more, read Micah Walter's blog post.
5. What performance improvements do the new EC2 M8idn/M8idb and R8idn/R8idb instances offer?
The new Amazon EC2 M8idn/M8idb and R8idn/R8idb instances are powered by custom sixth-generation Intel Xeon Scalable processors available only on AWS, combined with the latest sixth-generation AWS Nitro cards. These instances deliver up to 43% better compute performance per vCPU compared to previous-generation instances. The M8idn/R8idn variants offer up to 600 Gbps network bandwidth, while the M8idb/R8idb variants provide up to 300 Gbps EBS bandwidth. This makes them ideal for compute-intensive and memory-intensive workloads that demand high throughput and low latency. Whether you're running big data analytics, high-performance computing, or large-scale databases, these instances can significantly boost performance.
6. What celebrates two years for Valkey and what milestones has it achieved?
Valkey, the open-source in-memory data structure store, celebrates its second birthday with impressive growth. It stands as proof that community-driven technology can innovate faster and scale further than single-vendor models. Key milestones include surpassing 100 million Docker pulls (a 17x increase year over year) and attracting more than 225 contributors who have submitted over 1,000 code contributions. This rapid adoption underscores Valkey's reliability and performance for caching, session management, and real-time analytics. The active community continues to enhance the project with new features and optimizations.