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

patronus/capabilities

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.

Patronus telemetry metadata in AI SDK generateText

Pass a telemetry object to generateText with functionId (span name) and metadata (custom attributes) properties. Every attribute inside metadata becomes an OTEL attribute and is indexed by Patronus for filtering.

Patronus evaluation example with lynx evaluator

Patronus provides automated evaluations. The lynx evaluator can check for the 'patronus:hallucination' criteria. Make a POST request to https://api.patronus.ai/v1/evaluate with evaluators array, evaluated_model_input, evaluated_model_output, and the trace_id and span_id from the current span context to link the evaluation to your trace.

Patronus production monitoring features

Patronus supports production monitoring and alerting through viewing logs and traces, and by configuring webhooks for alerting. For agent tracing, Patronus's AI assistant Percival assists with error analysis and prompt optimization.

Give your agent this brain