Home icon

How Cato Networks uses Amazon Bedrock to transform free text search into structured GraphQL queries

Machine Learning Blog



Cato Networks has leveraged Amazon Bedrock to transform free text search into structured GraphQL queries for their SASE management console's events page. This innovation allows users to perform more intuitive searches across network and security events.

  • Used a custom JSON schema to validate and structure natural language queries
  • Implemented prompt engineering with Amazon Bedrock to convert text to structured filters
  • Selected Anthropic's Claude model based on accuracy, latency, and cost
  • Created a Natural Language Search service to bridge the management console and Bedrock
  • Reduced query time from minutes to near-instantaneous results

The solution enables users with minimal product knowledge to quickly find and filter events, improving overall user experience and efficiency in data management.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Feb 17
2025
Implementing Semantic Search using Amazon Bedrock and RDS for PostgreSQL in .NET
Dec 4
2024
Amazon Bedrock Knowledge Bases now supports structured data retrieval
Jan 2
2025
Analyze blockchain data with natural language using Amazon Bedrock
Feb 21
2025
Improve search results for AI using Amazon OpenSearch Service as a vector database with Amazon Bedrock

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.