Platform WatchJune 24, 2026via AWS Machine Learning Blog
Build a healthcare appointment agent with Amazon Nova 2 Sonic
Why it matters
AWS is pushing agentic AI from research into production via Amazon Nova 2 Sonic + Bedrock AgentCore. This sample-to-deployment pattern signals how enterprises will operationalize voice agents for high-volume, regulated workflows without custom infrastructure.
Key signals
- Amazon Nova 2 Sonic enables voice-based agentic workflows
- Framework handles patient authentication, appointment management (confirm/cancel/reschedule), pre-visit health data collection, human escalation
- Targets reduction of healthcare no-show rates at scale
- Browser-based testing interface included
- Integration pathway to telephony via Amazon Connect Customer for outbound dialing
- Tool orchestration and voice conversation as core agentic capabilities
- Published June 24, 2026 on AWS ML blog (production announcement format)
The hook
Not a chatbot demo. Amazon just shipped a voice agent framework that handles real healthcare workflows — authentication, scheduling, escalation.
In this post, you will learn how to build a voice agent that handles appointment reminder conversations using Amazon Nova 2 Sonic and Amazon Bedrock AgentCore. The agent authenticates patients by voice, manages appointments (confirm, cancel, or reschedule), collects pre-visit health information, and escalates to human staff when needed. You handle routine calls at scale, which can help reduce no-show rates. This sample focuses on the agentic side of the problem: voice conversation and tool orchestration. A browser-based interface is included for testing. To connect the agent to actual phone lines for outbound dialing, you would integrate a telephony service such as Amazon Connect Customer.