new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

confident-ai/options

3 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Confident AI configureAiSdkTracing trace attributes

The configureAiSdkTracing function accepts the following trace attributes: name (string), threadId (string), userId (string), and environment (string). These attributes make it easier to find and filter traces.

Confident AI configureAiSdkTracing confidentPrompt option

Pass a Prompt object to configureAiSdkTracing with the confidentPrompt parameter to associate traces with a specific prompt version from Confident AI Prompt Management. The prompt must be pulled before passing it to configureAiSdkTracing.

Confident AI online evaluations: metric collections

Confident AI supports automatic online evaluation of traces by passing metric collection names to configureAiSdkTracing. Three metric collection options are available: metricCollection (for trace level), llmMetricCollection (for LLM span level), and toolMetricCollection (for tool span level). Metric collections must be created in the Confident AI platform first.

Give your agent this brain