- Automated Metrics - Configure metrics in the Atla UI that we run automatically and scalably using LLMs-as-a-Judge.
- Programmatic Metrics - Log metrics directly from your code using the Atla SDK.
Supported Data Types
The permitteddata_type
fields are:
Data Type | Description | Expected Value |
---|---|---|
likert_1_to_5 | A numeric 1-5 scale | int between 1 and 5 |
boolean | A boolean scale | bool (True/False) |
Automated Metrics
Automated metrics allow you to configure custom evaluations directly in the Atla UI without modifying your code. These metrics run automatically on your traces at the trace level using LLMs-as-a-Judge (LLMJ), evaluating the entire conversation or interaction flow. Atla has a research specialization in building frontier LLMJs, check out our Selene model family. You may initialize any number of custom, automated metrics. To create one:- Configure in UI: Navigate to the
Metrics
tab in the Atla UI, and selectCreate Metric
. - Define attributes: Define the name, data type, and fraction of traces on which it should run.
- Define evaluation criteria: Provide your custom evaluation prompt.
- Advanced attributes: Define metadata filters to which the metric applies.