Seismic information evaluation is an integral part of power exploration, however configuring advanced processing workflows has historically been a time-consuming and error-prone problem. Halliburton’s Seismic Engine, a cloud-native software for seismic information processing, is a robust device that beforehand required guide configuration of roughly 100 specialised instruments to create workflows. This course of was not solely time-consuming but in addition required deep experience, doubtlessly limiting the accessibility and effectivity of the software program.
To deal with this problem, Halliburton partnered with the AWS Generative AI Innovation Middle to develop an AI-powered assistant for Seismic Engine. The answer makes use of Amazon Bedrock, Amazon Bedrock Information Bases, Amazon Nova, and Amazon DynamoDB to remodel advanced workflow creation into conversations. Geoscientists and information scientists can configure processing instruments by way of pure language interplay as an alternative of guide configuration.
On this publish, we’ll discover how we constructed a proof-of-concept that converts pure language queries into executable seismic workflows whereas offering a question-answering functionality for Seismic Engine instruments and documentation. We’ll cowl the technical particulars of the answer, share analysis outcomes exhibiting workflow acceleration of as much as 95%, and talk about key learnings that may assist different organizations improve their advanced technical workflows with generative AI.
Our collaboration with AWS has been instrumental in accelerating subsurface interpretation workflows. By integrating Amazon Bedrock providers with Halliburton Landmark’s DS365 Seismic Engine, we have been capable of scale back historically time‑consuming workflow‑constructing duties by an order of magnitude. This generative AI–powered workflow assistant not solely improves effectivity and accuracy but in addition makes our superior geophysical instruments extra accessible to a broader vary of customers. The scalable cloud‑native structure on AWS has enabled us to ship a seamless, conversational expertise that essentially improves productiveness throughout subsurface workflows.
— Phillip Norlund, Supervisor of Subsurface Applied sciences, Halliburton Landmark
— Slim Bouchrara, Senior Product Proprietor of Subsurface R&D, Halliburton Landmark
Resolution overview
Our venture aimed to handle two key targets: remodeling pure language queries into executable seismic workflows, and offering an clever query and reply (Q&A) system for Seismic Engine documentation. To attain this, we developed an answer utilizing Amazon Bedrock that allows geoscientists to work together with advanced seismic instruments by way of pure dialog.The spine of our system is a FastAPI software deployed on AWS App Runner, which handles consumer queries by way of a streaming interface. When a consumer submits a question, an intent router powered by Amazon Nova Lite analyzes the request to find out whether or not it’s looking for workflow technology or technical data. For Q&A requests, the system makes use of Amazon Bedrock Information Bases with Amazon OpenSearch Serverless to offer related solutions from listed documentation. For workflow requests, a technology agent utilizing Anthropic’s Claude on Amazon Bedrock creates YAML workflows by choosing from 82 accessible Seismic Engine instruments.
To keep up context and allow multi-turn conversations, we built-in Amazon DynamoDB for chat historical past and interplay logging. The system helps streaming responses for each Q&A and workflow technology, offering fast suggestions to customers because the system processes their requests. This structure permits advanced technical workflows to be created and modified by way of pure dialog, whereas sustaining the exact management required for seismic information processing. The next diagram illustrates the answer structure.
Question routing and intent classification
After the consumer’s question is offered to the system, the Intent Router classifies the intent label of the given question by calling Amazon Nova Lite through the Amazon Bedrock API. The big language mannequin (LLM) is given a immediate to provide certainly one of three intent labels: “Workflow_Generation”, “QnA”, and “General_Question”.The “Workflow_Generation” label is used to route queries associated to workflow technology, together with studying/loading datasets, information processing operations, and numerous requests involving manipulating particular datasets. The “QnA” intent label is used for questions associated to particular instruments, requests for pattern workflows, or questions on Seismic Engine documentation. The “General_Question” label is reserved for queries unrelated to Seismic Engine operations or workflows.In our implementation, Amazon Nova Lite carried out the routing process effectively, providing a superb stability between accuracy and latency.
Query answering implementation
The Q&A element handles Seismic Engine-related queries through the use of Amazon Bedrock Information Bases, a totally managed service for end-to-end Retrieval Augmented Era (RAG) workflow. We selected Bedrock Information Bases as a result of it alleviates the operational overhead of managing vector databases, chunking methods, and embedding pipelines. As a totally managed service, it handles infrastructure scaling, safety, and upkeep mechanically, in order that our workforce might deal with answer growth somewhat than RAG infrastructure operations. The service offers native assist for a number of chunking methods together with hierarchical chunking, which maintains parent-child relationships to stability granular retrieval with broader doc context.The information sources embody device documentation markdown recordsdata and Seismic Engine manuals saved in S3. We stored device documentation recordsdata unchunked since they’re comparatively quick, preserving full context for particular person instruments. For longer paperwork like Seismic Engine manuals, we used hierarchical chunking with default settings. We use Amazon Titan Textual content Embeddings V2 for embedding technology and OpenSearch Serverless because the vector database. The system additionally shops metadata corresponding to file names, URLs, and doc sorts for every listed merchandise for downstream use.For each retrieval and response technology, we use Amazon Bedrock Information Bases’ retrieve_and_generate API with Claude 3.5 Haiku because the mannequin. The system helps multi-turn conversations by sustaining session context, and responses are formatted with inline citations for enhanced traceability.
Notice: This answer was developed and evaluated utilizing Claude 3.5 Sonnet V2 and Claude 3.5 Haiku. Since then, these fashions have been succeeded by Claude Sonnet 4.5 and most not too long ago Claude Sonnet 4.6, in addition to Claude Haiku 4.5, all accessible by way of Amazon Bedrock. The answer structure helps mannequin upgrades with out code adjustments, as a way to use the most recent mannequin capabilities.
This strategy allows our system to offer context-aware, related solutions to consumer queries about Seismic Engine instruments and workflows.
Workflow technology
For queries categorised as “Workflow_Generation”, our answer makes use of LLM brokers to transform pure language into executable YAML workflows. The agent is sure with 82 instruments accessible on Seismic Engine. Primarily based on the consumer’s question and power specs that outline inputs, parameters, and outputs, the agent selects acceptable instruments, determines their appropriate execution order, and generates a YAML workflow that addresses the consumer’s necessities. The next determine illustrates the workflow technology course of.
We used each Claude 3.5 Sonnet V2 and Claude 3.5 Haiku in our implementation, orchestrated by way of the LangChain framework for agent administration and power binding. The fashions are supplied with detailed device descriptions and specs, in order that they’ll perceive every device’s capabilities and necessities. When producing workflows, the system considers not solely the express necessities within the consumer’s question but in addition consists of needed default parameters when particular values aren’t offered.The workflow technology course of helps multi-turn conversations, in order that customers can modify beforehand generated workflows by way of pure language requests. Through the use of dialog historical past saved in Amazon DynamoDB, the LLM can both generate new workflows or modify current ones in response to the consumer’s present question.
Analysis
To guage our answer’s effectiveness, we created a complete take a look at dataset of query-workflow pairs, consisting of each low and medium complexity workflows. These have been derived from actual historic workflows and validated by subject material consultants to confirm they precisely signify typical consumer requests.
Workflow technology outcomes
| Mannequin | Complexity | Success Charge | Imply Era Time (s) | Median Era Time (s) |
| Claude Haiku 3.5 | easy | 84% | 8.3 | 5.9 |
| medium | 90% | 12.4 | 9.1 | |
| Claude Sonnet 3.5 V2 | easy | 86% | 11.2 | 11.5 |
| medium | 97% | 15.8 | 16.6 |
Each fashions demonstrated robust efficiency, with Claude Sonnet 3.5 V2 exhibiting superior success charges, significantly for medium complexity workflows. The system delivers responses by way of streaming, offering customers with fast suggestions because the workflow is generated, with full workflows delivered inside 5.9-16.6 seconds. Claude Haiku 3.5 presents quicker technology occasions, offering a trade-off choice between velocity and accuracy.
Comparability to baseline efficiency
| Consumer Sort | % Success | % Failure | Time to Construct Easy Move (min) | Time to Construct Advanced Move (min) |
| New Consumer | 70% | 20% | 4 | 20 |
| Skilled Consumer | 85% | 10% | 2 | 5 |
| Our Resolution | 84-97% | 3-16% | 0.13-0.26 | 0.21-0.28 |
Our generative AI answer demonstrates the next enhancements:
- Success charges of 84-97% surpass each new and skilled customers.
- Workflow creation time is diminished from minutes to seconds, representing over a 95% time discount.
These outcomes display that customers throughout expertise ranges can improve productiveness by over 95%, whereas sustaining or exceeding the accuracy of guide workflow creation.
Conclusion
On this publish, we confirmed how we used Amazon Bedrock to remodel advanced technical processes into pure conversations. By implementing an AI-powered assistant with built-in Q&A capabilities, we achieved workflow technology success charges of 84-97% whereas decreasing creation time by over 95% in comparison with guide processes. The system’s means to deal with each low and medium complexity workflows, mixed with its contextual understanding of Seismic Engine instruments, demonstrates how generative AI can enhance industrial software program usability with out compromising accuracy.
This strategy additionally generalizes nicely to different domains with advanced, multi-step agentic workflows requiring specialised device data and configuration. As subsequent steps, think about exploring multi-agent architectures utilizing frameworks like Strands Agents SDK with Amazon Bedrock AgentCore for improved accuracy by way of specialised sub-agents.
In regards to the authors
