We’re happy to announce that the industry’s first APM for AI, New Relic AI monitoring, is now available to all our customers.
New Relic AI monitoring gives you deep insights and unprecedented visibility across your entire AI stack, so you can build and run AI applications with confidence. You can now take advantage of:
- Auto instrumentation: New Relic agents come equipped with all AI monitoring capabilities, including full AI stack visibility, response tracing, model comparison, and simplified set-up for popular AI frameworks like OpenAI, Bedrock, and LangChain across Python, Node.js, Ruby, and Go languages.
- Full AI stack visibility: Holistic view across the application, infrastructure, and the AI layer, including AI metrics like response quality and token counts. View all this alongside APM golden signals.
- LLM response overview with end-user feedback: Quickly identify trends and outliers in LLM responses with a consolidated view. Sentiment analysis and actual user feedback are now displayed alongside AI responses, empowering you to prioritize areas for improvement, ensure unbiased outputs, and maintain user trust.
- Deep trace insights for every response: Trace the lifecycle of complex LLM responses built with tools like LangChain to fix performance issues and quality problems such as bias, toxicity, and hallucination.
- Enhanced data security: Safeguard sensitive data (PII) sent to your AI application with the new drop filter functionality that allows you to selectively exclude specific data types from monitoring, ensuring compliance and protecting user privacy.
- Optimized model performance and cost: Compare performance and cost across models or services in a single view to choose the model that best fits your need.