Last week, AWS brought together AWS Heroes from around the world for the annual AWS Heroes Summit—an invite-only gathering where global experts in AI, serverless, and containers collaborate directly with AWS product and service teams. Day 1 featured a fireside chat with AWS CEO Matt Garman, followed by an AMA with James Hamilton on Day 2.
New AWS announcements
Web Search on Amazon Bedrock: Amazon Bedrock now enables OpenAI models (GPT-5.4, GPT-5.5, and GPT-5.6 Sol/Terra/Luna) to browse and retrieve information from the internet. This allows AI applications to access up-to-date information beyond their training data while maintaining data residency within your secured AWS environment with zero data egress.
Runtime instances for AI agents: You can now deploy and run AI agents on dedicated runtime instances through Amazon Bedrock AgentCore, providing more control over agent execution environments with predictable performance and cost. Runtime instances provide AWS-managed EC2 infrastructure where you deploy multiple agents in a single runtime, each with their own dependencies and artifact types. Agents can collaborate on the same host within shared sessions that persist for up to 14 days, with GPU acceleration support and session stop/restart to save costs during idle periods.
Vector search in DynamoDB: You can now store and query vector embeddings alongside your existing data in DynamoDB without managing a separate vector database. DynamoDB already supports storing memory for AI agents, and with vector search you can now add semantic retrieval over that memory for agentic grounding, with predictable performance.
Technical debt remediation: This new capability helps engineering teams analyze and remediate technical debt across source code repositories at scale. You can modernize mainframe and legacy workloads with an ongoing, automated approach rather than a one-time migration event.
Lambda network bandwidth increase: AWS Lambda functions now support increased network bandwidth, enabling data-intensive workloads and faster communication between Lambda functions and other AWS services. Functions outside a VPC configured with 2 GB of memory or more can access network bandwidth that scales proportionally, from 625 Mbps at 2 GB up to 3,000 Mbps at 10 GB.
Additional projects and news
Dogwood: AWS open-sourced Dogwood, a purpose-built governance language for AI agents that supports Cedar policies and adds temporal conditions. Powering Dogwood, Amazon Bedrock AgentCore introduced agents whose decisions depend on the history of an agent's actions within a session, not on the current request alone.
Agent Plugins: AWS announced support for Agent Plugins, an open source, vendor-neutral specification that gives AI agent extensions a common packaging format so you can package an extension once and ship it to any client, including Kiro, VS Code, Cursor, or any tool that implements the spec.
Kiro Crew: Kiro Crew is a persistent, self-evolving workspace that keeps work moving, online or offline, enabling collaborative multi-agent development workflows within the Kiro IDE. It's built for engineering work that goes beyond a single chat session and spans repos, tools, and days. You can run several efforts in parallel or hand work to subagents that report back, so nothing waits in line.
For a full list of AWS announcements, keep an eye on the AWS News Blog.