基于企业数据的GenAI构建：AWS AgentCore + Coveo（由Coveo赞助）.pdf

1、 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.Nicolas BordeleauGrounding GenAI on Enterprise Data with AWS AgentCore&CoveoHead of Product Relati

2、onsCoveoM A M 2 2 1-S 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.Why grounding GenAI is so importantArchitecture:Coveo+Bedrock AgentCoreThe secret sauceNext stepsAgenda 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affi

3、liates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.Generative AI Q&A SolutionFully managed RAG solution-Powered by Amazon N

4、ovaCustom GenAI and Agentic applicationsGround your own LLM-based/Agentic Application on your Enterprise DataCoveo AI-Relevance PlatformMCPShopping cart-Free transport iconsUnified IndexPermission-AwareHybrid RelevanceBehavioral AnalyticsFully CustomizableBedrockAgentCoreQ BusinessQuick Suite 2025,A

5、mazon Web Services,Inc.or its affiliates.All rights reserved.Gen AIAgentic AI Primary purpose:Content generation Dependency:Prompts and input dataAgency level:None(requires more human prompting)Ability to execute workflows:None/lowPrimary purpose:Goal achievementDependency:Access to tools,data and a

6、gentsAgency level:Higher(less to no human oversight)Ability to execute workflows:Medium/highAgentic AI will help realize the true promise of LLMs 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.Why LLM need to be grounded?Factual AccuracyContextual RelevanceTraceability and TrustD