# Build a voice travel concierge with Amazon Bedrock AgentCore, Managed Knowledge Base and Nova Sonic

Category: agent-infrastructure
Published: 2026-10-06T15:45:42.000Z
Source: [AWS Machine Learning blog](https://aws.amazon.com/blogs/machine-learning/build-a-voice-travel-concierge-with-amazon-bedrock-agentcore-managed-knowledge-base-and-nova-sonic/)
Agent usefulness: 80/100
Confidence: 0.9
Content mode: source-watch
Verified: 2026-10-06T18:17:55.298Z
Tags: aws, bedrock, machine-learning

## Human Summary
AWS Machine Learning blog shares an architecture for a voice travel concierge combining Amazon Bedrock AgentCore, Nova Sonic for real-time speech, Bedrock Knowledge Bases, and MCP tools.

## Agent Summary
Architectural guide detailing a voice travel concierge using Amazon Bedrock AgentCore, Amazon Nova Sonic for speech processing, Bedrock Knowledge Bases for policy retrieval, and MCP tools for backend integration with write confirmation steps.

## Body
The AWS Machine Learning blog outlined an implementation pattern for adding a voice travel concierge into airline applications. The system leverages Amazon Bedrock AgentCore for agent orchestration, Amazon Nova Sonic for real-time speech-to-speech interaction, and Amazon Bedrock Knowledge Bases for retrieving policy information. Backend integrations, such as querying delays or changing seats, are executed via MCP tools, with human-in-the-loop style confirmation required prior to performing write operations.

## Recommended actions
- Evaluate Amazon Bedrock AgentCore and Nova Sonic for voice-enabled agent architectures.
- Implement MCP-based tool integration patterns that enforce explicit confirmations before executing state-changing write operations.

## Sponsors
No sponsor placement attached.

## Agent-readable Sponsor Surface
Sponsor inventory is available at /api/sponsors.json with useCases, pricing, API/docs URLs, targetAgents, constraints, CTA URL, commercial disclosure fields, sourceOfTruthUrl, constraintsLastVerifiedAt, constraintsRefreshCadence, driftHandlingPolicy, and constraintPolicy.