"Before adopting AIM, the team tracked their agents' health manually, requiring engineers to write custom code for telemetry, which was inefficient and time-consuming. The debugging process was long and manual."
"By adopting AIM, the New Relic engineering team simplified their operations with a smooth and quick onboarding process that required only a minor configuration change to our APM Python agent."
"The team uses the model inventory to test changes in staging, comparing the impact on response times and token usage before pushing to production, ensuring optimal performance."
"The team monitors token usage averages and P95 to ensure they are staying within context limitations, which is crucial for cost optimization and efficient AI agent management."
New Relic's internal engineering and data science team transitioned from manual debugging to integrated AI observability using New Relic AI Monitoring (AIM). Previously, they tracked agent health manually, which was inefficient. With AIM, they simplified operations and improved onboarding with minimal configuration changes. The team utilizes AIM for various use cases, including monitoring model performance during transitions and optimizing costs by tracking token usage averages, ensuring efficient management of AI agents in their environment.
Read at New Relic
Unable to calculate read time
Collection
[
|
...
]