AWS launches AgentCore platform for building voice AI agents with Amazon Nova 2 Sonic
AWS has released AgentCore, a new platform for hosting and running voice-based AI agents, integrated with Amazon Nova 2 Sonic for real-time speech capabilities. The platform uses the open Model Context Protocol (MCP) to connect agents to backend systems and deploys each conversation in isolated microVMs.
AWS launches AgentCore platform for building voice AI agents with Amazon Nova 2 Sonic
AWS has released AgentCore, a new platform for hosting and running voice-based AI agents integrated with Amazon Nova 2 Sonic for real-time speech processing. The platform uses the Model Context Protocol (MCP) to connect agents to backend systems, according to AWS.
Platform architecture
AgentCore consists of two main components: AgentCore Runtime, which hosts conversation logic with each call running in an isolated microVM, and AgentCore Gateway, which exposes backend APIs as MCP tools that agents can discover and invoke. The system integrates with Amazon Nova 2 Sonic to handle bidirectional speech-to-speech interaction, including transcription, turn-taking, and interruptions in a single stream.
The platform supports both text and audio as input and output formats. AWS deploys the system on Amazon ECS with AWS Fargate, with telephony integration through Amazon Chime SDK Voice Connector providing SIP trunk and toll-free number capabilities.
Technical implementation
The reference architecture AWS published demonstrates a restaurant ordering system with three distinct layers: telephony (handling phone network audio and caller identification), agent (running conversations with Amazon Nova 2 Sonic), and backend (menu, carts, orders, locations). Audio streams from the phone network through a SIP gateway to the agent layer over signed WebSocket connections.
AgentCore Runtime invokes AWS Lambda functions to build system prompts stored in AWS Systems Manager Parameter Store, customizing them based on session identifiers and customer data from Amazon DynamoDB. The platform warms agent sessions while phones are still ringing to eliminate dead air for callers.
Deployment and infrastructure
The full stack deploys through AWS CDK, with container images built via AWS CodeBuild and stored in Amazon ECR. The backend layer uses Amazon API Gateway fronting REST endpoints secured by IAM, with AWS Lambda executing business logic and Amazon DynamoDB for data storage. Amazon Location Service handles geocoding and route calculation in the reference implementation.
According to AWS, the SIP gateway runs on Amazon ECS on AWS Fargate behind a Network Load Balancer, accepting SIP invites over TCP port 5060 and allocating Real-time Transport Protocol (RTP) service ports for media reception.
What this means
AgentCore represents AWS's entry into the voice AI agent infrastructure market, competing with platforms like Retell AI and Bland AI. The use of MCP as the standard protocol for connecting agents to tools allows backend systems to change without redeploying agents, and new channels like mobile apps or kiosks can connect to the same agent without backend rewrites. The microVM isolation model addresses security and multi-tenancy concerns that have slowed enterprise adoption of voice agents. Pricing for AgentCore has not been disclosed, though it will likely bundle compute costs with Amazon Nova 2 Sonic inference charges.
Related Articles
Amazon Nova Act Brings Vision-Based Web Navigation to UX Testing, No Hard-Coded Scripts Required
AWS has released a cloud-deployed UX testing platform built on Amazon Nova Act, a multimodal foundation model that navigates web interfaces through visual understanding rather than hard-coded selectors. The solution processes documentation with Claude 4.5 Sonnet to generate test scenarios, executes parallel testing via ECS, and analyzes results automatically, addressing the scalability limitations of manual testing and maintenance overhead of traditional automation tools.
GitHub Copilot for Visual Studio adds MCP server trust layer and C++ support
GitHub released its June 2026 update for Copilot in Visual Studio, adding a trust layer for Model Context Protocol (MCP) servers, improved usage analytics visibility, and the first C++ language scenarios for the AI coding assistant.
AWS Extends QA Studio with Test Suites and CI/CD CLI for Automated Regression Testing
AWS has extended its QA Studio reference solution with test suite functionality and a command-line interface for CI/CD integration. The updates enable parallel execution of regression tests on Amazon ECS Fargate and bring Amazon Nova Act-powered visual testing into automated deployment pipelines.
AWS Adds NVIDIA Nemotron 3 Nano (30B) and Super (120B) to SageMaker Serverless Fine-Tuning
Amazon SageMaker AI now supports serverless fine-tuning for NVIDIA Nemotron 3 Nano (30B parameters, 3B active) and Nemotron 3 Super (120B parameters, 12B active). The integration includes supervised fine-tuning, reinforcement learning with verifiable rewards (RLVR), and reinforcement learning from AI feedback (RLAIF).
Comments
Loading...