AWS Expands Agentic AI Strategy With New Tools and Investments
At a glance
- AWS is investing in agentic AI technologies and services
- Frontier agents like Kiro and Security Agent have been launched
- $1 billion allocated to Forward Deployed Engineering for AI deployments
AWS is expanding its approach to agentic AI by introducing new technologies, enhancing existing tools, and investing in deployment strategies for enterprise customers. These developments reflect a broader effort to support automation and operational efficiency through advanced AI capabilities.
Swami Sivasubramanian serves as Vice President for Agentic AI at AWS, overseeing the development of services such as Amazon Quick, Kiro, Bedrock AgentCore, DevOps Agent, Security Agent, and Amazon Transform. He previously led the company’s wider AI and machine learning portfolio, which included Amazon SageMaker and Amazon Bedrock. From May 2022 to May 2025, Sivasubramanian participated as a member of the U.S. National Artificial Intelligence Advisory Committee.
AWS has introduced autonomous AI agents, known as frontier agents, including Kiro, AWS Security Agent, and AWS DevOps Agent. These agents are designed to operate independently for extended periods and assist with software development, security, and operational tasks. The company is also expanding its agentic AI ecosystem with new services like AWS Continuum, AWS Context, and mobile orchestration for Kiro, as announced at AWS Summit New York 2026.
To accelerate the adoption of agentic AI, AWS established a $1 billion Forward Deployed Engineering (FDE) organization. This initiative embeds AI engineers directly with customers to support the deployment and scaling of agentic AI solutions. AWS is also enhancing Bedrock AgentCore with features such as Agent Registry, managed agent harness, policy controls, and automated evaluations to help organizations deploy production-ready agents.
What the numbers show
- $1 billion invested in Forward Deployed Engineering for AI
- Amazon Quick Suite deployed to 120,000 DXC Technology users
- Vertiv expanded Amazon Quick Suite usage by over 25% in 2026
- AWS Well-Architected Agentic AI Lens published in June 2026
- Prescriptive guidance on agentic AI published in April 2026
Amazon Quick Suite, an agentic AI application focused on automating workplace tasks, has been adopted by organizations such as DXC Technology and Vertiv. DXC Technology uses the suite across 120,000 users, while Vertiv increased its deployment by more than 25% during 2026. These deployments illustrate the growing use of agentic AI tools in large-scale enterprise environments.
In June 2026, AWS published the Well-Architected Agentic AI Lens to provide organizations with guidance on securely designing, deploying, and operating agentic AI systems at scale. Additionally, prescriptive guidance released in April 2026 offers recommendations for governing and architecting agentic AI in enterprise settings.
Ongoing enhancements to Bedrock AgentCore are intended to support the development and operation of production-ready agents. New features include an Agent Registry, managed agent harness, policy controls, and automated evaluation processes. These additions aim to streamline the deployment and management of agentic AI solutions across various business functions.
Swami Sivasubramanian was recognized by Fast Company as one of their “AI 20” for 2026, highlighting his leadership in implementing agentic AI at scale. His current responsibilities at AWS include overseeing the expansion and integration of agentic AI capabilities across the company’s cloud services.
* This article is based on publicly available information at the time of writing.
Sources and further reading
- Swami Sivasubramanian | Artificial Intelligence
- About the Author
- Swami Sivasubramanian - VP, AWS Agentic AI | LinkedIn
- Agentic AI Lens - AWS Well-Architected - Agentic AI Lens
- Amazon.com, Inc. - Amazon.com Announces First Quarter Results
- AWS Summit New York 2026: New AI agent innovations
Note: This section is not provided in the feeds.
More on Technology
-
US Lawmakers Advance Measures Targeting Foreign Humanoid Robots
The House passed a defense bill restricting humanoid robots from China, Russia, and Iran, reflecting national security concerns, according to reports.
-
Katy ISD Sets Grade-Based Limits for AI Use in Classrooms
Katy ISD's new AI Framework restricts generative AI use for K-6 students, allowing high schoolers limited access with teacher approval, starting 2026.
-
Self-Wearing Robotic Garment Demonstrated by KAIST and Stanford Researchers
A prototype of the SWAG robotic garment system was showcased in South Korea. It assists users in dressing using inflatable tubes, researchers reported.