In this episode of AWS Partners Unplugged, we explore four innovative collaborations between AWS and its partners showcased in recent APN blogs. We highlight how Dynatrace provides comprehensive observability for generative AI applications built on Amazon Bedrock, ensuring reliable and compliant AI operations with features like guardrail analysis and audit trails. We then examine how AWS and Intel are making large language models more accessible and cost-effective through model distillation and CPU optimizations. We also discuss MongoDB Atlas's impressive 14x improvement in search indexing performance by leveraging Amazon S3 for index snapshots, and conclude with an exploration of an AI assistant for Splunk that transforms natural language queries into efficient search queries using Amazon Bedrock agents. Throughout the episode, we emphasize how these technical innovations deliver tangible business value by addressing real-world challenges for partners and their customers.

The blog links:

• https://aws.amazon.com/blogs/apn/elevating-llm-observability-with-amazon-bedrock-and-dynatrace/
• https://aws.amazon.com/blogs/apn/how-aws-and-intel-make-llms-more-accessible-and-cost-effective-with-deepseek/
• https://aws.amazon.com/blogs/apn/improving-mongodb-atlas-search-elasticity-with-amazon-s3/
• https://aws.amazon.com/blogs/apn/unlocking-the-power-of-splunk-with-amazon-bedrock-an-agentic-ai-approach-to-build-customized-splunk-assistants-using-bedrock-agents/

To reach us: aws-partner-unplugged-podcast-hosts@amazon.com