NVIDIA NeMo Relay for Agent Tracing
This practical demonstration shows how to quantify the effort AI agents expend to reach correct answers, a crucial metric for optimizing performance. Developers can apply these tracing techniques to their own agent implementations, comparing efficiency across different approaches and identifying optimization opportunities.
NVIDIA collaborated with NousResearch on a hands-on walkthrough of NVIDIA NeMo Relay to collect traces for Hermes Agent.
The walkthrough includes two example scenarios that follow the agent's calls and retries.Users can view the full trace in Arize Phoenix and see how Nous used traces and task results to evaluate fixes across repeated runs.
Your agent got the right answer. How much work did it take to get there? We worked with @NousResearch / @Teknium on a hands-on walkthrough of NVIDIA NeMo Relay to collect traces for Hermes Agent. Run two example scenarios, follow the agent’s calls and retries, and see the full trace in Arize Phoenix. The blog also looks at how Nous used traces and task results to evaluate fixes across repeated runs. TechBlog: nvda.ws/47tKxjQ 📽️ by our own @Picomoorhead :
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include NeMo Relay, Hermes Agent, Arize Phoenix, agents.
Source attribution: curated from NVIDIA AI (@NVIDIAAI). Cross-source corroboration: 11 independent sources have covered this development (including AWS Machine Learning Blog, LangChain, techcrunch), confirming industry-wide signal strength.