Halliburton enhances seismic workflow creation with Amazon Bedrock and Generative AI
Machine Learning Blog
This article describes how Halliburton partnered with AWS to build an AI-powered assistant for their Seismic Engine using Amazon Bedrock and generative AI to streamline seismic workflow creation.
- Converts natural language queries into executable YAML seismic workflows automatically
- Uses Amazon Nova Lite for intent routing between workflow generation and Q&A requests
- Implements Amazon Bedrock Knowledge Bases with OpenSearch for documentation Q&A
- Achieves 84-97% workflow generation success rates across complexity levels
- Reduces workflow creation time by over 95% compared to manual configuration
- Supports multi-turn conversations using Amazon DynamoDB for chat history
- Deployed on AWS App Runner with streaming responses for immediate user feedback
The solution demonstrates how generative AI can transform complex technical processes into conversational interfaces, enabling geoscientists to create seismic workflows in seconds rather than minutes while maintaining accuracy.
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
2025
2024
2025
2024
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.