Resources

The following resources provide additional context, technical details, and implementation guidance to support your organization's generative AI journey. As AWS continues to innovate with generative AI, you can regularly check these resources for updates and new capabilities.

AWS Prescriptive Guidance

Strategy resources

• Generative AI workload assessment

• Maturity model for adopting generative AI on AWS

• Retrieval Augmented Generation options and architectures on AWS

• Prompt engineering best practices to avoid prompt injection attacks on modern LLMs

RAG and chat-based assistants

• Choosing an AWS vector database for RAG use cases

• Deploy a RAG use case on AWS by using Terraform and Amazon Bedrock

• Develop advanced generative AI chat-based assistants by using RAG and ReAct prompting

• Develop a fully automated chat-based assistant by using Amazon Bedrock agents and knowledge bases

Coding assistants

• Use Amazon Q Developer as a coding assistant to increase your productivity

Document processing

• Document institutional knowledge from voice inputs by using Amazon Bedrock and Amazon Transcribe

• Automatically extract content from PDF files using Amazon Textract

AWS service documentation

• Amazon Bedrock documentation

• Amazon SageMaker AI documentation

Other AWS resources

• Transform your business with generative AI (AWS website)

• Generative AI innovation center (AWSwebsite)

• Securing generative AI: An introduction to the generative AI security scoping matrix (AWS blog post)

• Establishing an AI/ML center of excellence (AWS blog post)

• Architect defense-in-depth security for generative AI applications using the OWASP Top 10 for LLMs (AWS blog post)

• Setting up secure, well-governed machine learning environments on AWS (AWS blog post)

• Machine learning lens (AWS Well-Architected Framework)

Other resources

• OWASP top 10 for large language model applications (OWASP website)