How Twilio created SQL from Looker Modeling Language data using Amazon Bedrock | Amazon Web Services Machine Learning Blog

Introduction

Today’s leading companies trust Twilio’s Customer Engagement Platform (CEP) to build direct, personalized relationships with their customers everywhere in the world. Twilio enables companies to use communications and data to add intelligence and security to every step of the customer journey, from sales and marketing to growth, customer service, and many more engagement use cases in a flexible, programmatic way. Across 180 countries, millions of developers and hundreds of thousands of businesses use Twilio to create personalized experiences for their customers.

Virtual Assistant Development

Data is the foundational layer for all generative AI and ML applications. Managing and retrieving the right information can be complex, especially for data analysts working with large data lakes and complex SQL queries. To address this, Twilio partnered with AWS to develop a virtual assistant that helps their data analysts find and retrieve relevant data from Twilio’s data lake by converting user questions asked in natural language to SQL queries.

Use of Amazon Bedrock

Twilio implemented a virtual assistant tool using Amazon Bedrock, a fully managed generative AI service that provides access to high-performing foundation models (FMs) and capabilities like Retrieval Augmented Generation (RAG). This partnership highlighted how Twilio enabled natural language-driven data exploration of business intelligence (BI) data with RAG and Amazon Bedrock.

Workflow Implementation

The solution utilizes Amazon Bedrock, Amazon Relational Database Service (Amazon RDS), Amazon DynamoDB, and Amazon Simple Storage Service (Amazon S3). The workflow involves steps like model access, content ingestion, and the use of the RAG approach to retrieve relevant schema information from LookML metadata.

Enhancing Accuracy

To enhance the accuracy of the application and reduce inaccuracies, various measures were implemented based on user feedback. This led to an improved net promoter score (NPS) of 40, surpassing the initial target score set by the team.

Conclusion

In conclusion, the integration of generative AI technology has significantly enhanced the efficiency of data analysts at Twilio. By leveraging metadata for the data lake and innovative AI solutions, Twilio has streamlined data exploration and retrieval processes, ultimately empowering their teams to derive valuable insights from data with ease.