AI BriefingHow Hanatour Built a Travel Product Planning Agent Using Amazon Neptune and Amazon Bedrock AgentCore
Key point
Hanatour used Amazon Neptune and Amazon Bedrock AgentCore to cut travel product planning time from days to minutes.
Details
Hanatour built an AI agent system that lets product managers (MDs) complete travel package itinerary drafts—previously taking 2-3 days of manual work—in just 2-3 minutes.
Moving beyond a simple RAG approach, they adopted GraphRAG technology, which can capture complex relationships between data. To do this, they built a knowledge graph based on Amazon Neptune to improve search accuracy.
The key elements in the build process are as follows:
- Amazon Neptune: The underlying technology that stores the knowledge graph and processes complex relationship queries
- Amazon Bedrock AgentCore: The core framework that manages and executes the AI agent's workflow
- GraphRAG: Leverages graph structures to generate far more sophisticated, context-based answers than simple keyword search
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
AWS Releases 'Strands Harness' Based on Strands Agents SDK with Complete Agent Features Excluding Model Intelligence
ZEP Enhances Educational Quiz Generation Architecture with LangGraph on Amazon Bedrock AgentCoreUsing Codex on Amazon Bedrock