Create custom dashboards in LangSmith to track key metrics for your LLM app's performance such as cost, latency, and quality - including feedback from users or from online evaluation.

You can also compare data within a chart, whether it's comparing metrics with the same unit or the performance of different models or configurations on a single metric over time.

Drill into specific datasets with chart filters, and easily maintain your charts by saving, cloning, or editing them in LangSmith.

Read the docs for examples: https://docs.smith.langchain.com/how_to_guides/monitoring/dashboards

Try custom dashboards out here: smith.langchain.com/dashboards