New Relic announced that New Relic AI Monitoring (AIM), one of the industry’s first APM solution for AI-powered applications, is now integrated with Amazon Bedrock, a fully managed service by Amazon Web Services (AWS), that makes foundation models (FMs) from leading AI companies accessible via an API to build and scale generative AI applications. AWS customers can now use New Relic to gain greater visibility and insights across the AI stack, making it easier to troubleshoot and optimise their applications for performance, quality, and cost.
While AI is revolutionising modern applications, it introduces new challenges and complexity to organisation’s tech stacks. AI tech stacks include new components like large language models (LLMs) and vector data stores, and generate additional telemetry to track such as quality and cost. AIM solves these new challenges by bringing APM to the AI stack. Similar to how engineers monitor their application stack with New Relic APM, AIM provides engineers with full visibility into all components of the AI stack. AIM provides a single easy view to troubleshoot, compare, and optimise different LLM prompts and responses for performance, cost and tokens, and quality issues including hallucinations, bias, toxicity, and fairness across all models supported by Amazon Bedrock.
“AWS and New Relic are aligned in our efforts to empower every developer with the right tools to fuel their organisations’ adoption of AI. With New Relic AIM, developers can ensure best-in-class quality and performance when using popular LLMs like Anthropic,” said an executive from AWS. “With New Relic as a preferred vendor, AWS developers can make data-driven decisions when building AI-powered applications.”
AIM integrates with Amazon Bedrock to provide in-depth end-to-end observability. With AIM’s built-in integrations such as Langchain, Amazon Bedrock customers can get metrics and tracing throughout the life-cycle of LLM prompt and response, ranging from raw prompts to repaired and business-compliant responses.
Key features and use cases include:
⦁ 50+ (and growing) AI stack integrations: Instantly monitor your entire AI stack with quickstart integrations for popular LLMs, vector databases, and orchestration frameworks such as:
* Orchestration framework: Langchain
* Vector databases: Pinecone, Weaviate, Milvus, FAISS, Zilliz
* LLM: Amazon Bedrock (models from AI21 Labs, Amazon, Anthropic, and Cohere)
* AI infrastructure: Amazon SageMaker
⦁ Visibility across the entire AI app stack: Holistic view across the application, infrastructure, and the AI layer, including AI metrics like response quality and tokens alongside your APM golden signals, all with no additional instrumentation required.
⦁ Deep trace insights for every response: Trace the lifecycle of complex LLM responses built with tools such as Langchain including end-user feedback, to fix performance issues and quality problems such as bias, toxicity, and hallucination.
⦁ Compare performance and costs across models: Track usage, performance, quality, and cost across all models in a single view to choose the right model for your needs and optimise costs.
“Observability is essential for any company building AI applications,” said New Relic Chief Product Officer Manav Khurana. “Today’s news builds upon our deep work with AWS to bring the power of observability to engineers and developers who are modernising their tech stacks. And by putting our AI monitoring solution front and center with AWS customers, we are multiplying our ability to reach every engineer using leading LLMs like Anthropic.”