Mathew Monfort

Organizations face increasing pressure to scale generative AI development without sacrificing safety, accuracy, or speed. This session explores how to leverage the AWS Responsible AI Best Practice Framework to accelerate trusted AI application development.

With the newfound prevalence of applications built with large language models (LLMs) including features such as Retrieval Augmented Generation (RAG), agents, and guardrails, a responsibly-driven evaluation process is necessary to measure performance and mitigate risks.