How Druva used Amazon Bedrock to address foundation model complexity when building Dru, Druva’s backup AI copilot
Machine Learning Blog
This article discusses how Druva, a data resiliency cloud provider, used Amazon Bedrock to build Dru, their backup AI copilot that allows users to interact with Druva's software through natural language queries and conversation.
Specifically, the article covers:
- Overview of Dru and its capabilities like interactive reporting, intelligent responses, troubleshooting assistance, and simplified admin operations
- Challenges faced in building Dru, such as overall orchestration, identifying the right API route, generating API calls, and transforming data
- Druva's approach using a directed acyclic graph (DAG) with three streams: API route identification, API call generation, and data transformation
- Implementation details of each stream, including the use of prompts and foundation models
- Accuracy metrics achieved and future plans to scale the solution
- Conclusion highlighting the benefits of using Amazon Bedrock
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
Jun 27
2024
2024
Build generative AI applications on Amazon Bedrock — the secure, compliant, and responsible foundation
Dec 3
2025
2025
Amazon Bedrock adds reinforcement fine-tuning simplifying how developers build smarter, more accurate AI models
Jun 13
2025
2025
Build generative AI solutions with Amazon Bedrock
Oct 15
2025
2025
Amazon Bedrock simplifies access with automatic enablement of serverless foundation models
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.