Skip to main content

AWS Solutions Library

Guidance for Agentic Workflow Assistants on AWS

Overview

This Guidance demonstrates how to leverage generative AI to enhance operational efficiencies and drive innovation for energy organizations. It shows how to build agent-based assistants by incorporating large language model (LLM)-based agentic workflows for autonomous task execution. By analyzing diverse data points, including equipment failures, maintenance history, and supplier information, these agents can provide real-time decision support, generate actionable insights, and optimize operations

How it works

These technical details feature an architecture diagram to illustrate how to effectively use this solution. The architecture diagram shows the key components and their interactions, providing an overview of the architecture's structure and functionality step-by-step.

Download the architecture diagram

Well-Architected Pillars

The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.

Amazon Bedrock, Amazon Simple Storage Service (Amazon S3), Amazon Cognito, and AWS Amplify work together to improve productivity. Foundation models available on Amazon Bedrock deliver contextual information from company data sources, while Amazon S3 integrates for efficient data storage. Amazon Cognito handles secure user authentication, and Amplify streamlines deployment of resources and the web front-end.

Read the Operational Excellence whitepaper

Amazon Cognito provides robust authentication and authorization features. This fully managed service controls secure access while integrating seamlessly with other AWS services. Amazon Cognito also integrates with existing Active Directory instances, eliminating the need for additional log-ins and allowing you to maintain your current user accounts and configurations.

Read the Security whitepaper

Amazon Bedrock hosts generative AI models, agents, and knowledge bases, while Amazon Cognito manages user authentication and user pools. Amazon S3 stores knowledge base artifacts reliably, and AWS Amplify hosts front-end resources. This approach removes manual infrastructure management tasks, resulting in high availability and consistent performance.

Read the Reliability whitepaper

Amplify drives performance efficiency in this architecture. Amplify enhances performance by providing comprehensive development tools for building and deploying web and mobile applications, offering automated enhancements and optimized resource utilization.

Read the Performance Efficiency whitepaper

Amazon Bedrock offers a pay-per-token pricing model, which reduces costs by eliminating the need for infrastructure investments or model training costs. Amazon S3 provides flexible storage categories that optimize costs based on usage patterns. These tiered storage classes and lifecycle management features automatically move data to cost-effective storage tiers.

Read the Cost Optimization whitepaper

Amazon Bedrock and Amazon S3 minimize environmental impact through efficient resource utilization. Amazon Bedrock is a fully managed service that eliminates the need to run dedicated infrastructure for foundation models, creating a more sustainable approach than direct model hosting.

Read the Sustainability whitepaper

Disclaimer

The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.