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/setup

4 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 observability setup with OpenTelemetry

Patronus provides an end-to-end system to evaluate, monitor and improve performance of an LLM system. It exposes a fully-managed OTEL endpoint. Configure an OTLP exporter to point at the Patronus endpoint with your API key, and Patronus will automatically convert LLM spans into prompt/response records.

Patronus OTEL endpoint and API key environment variables

Configure these environment variables for Patronus observability: OTEL_EXPORTER_OTLP_ENDPOINT=https://otel.patronus.ai/v1/traces and OTEL_EXPORTER_OTLP_HEADERS="x-api-key:<PATRONUS_API_KEY>".

Patronus setup with @vercel/otel and OTLP HTTP exporter

To set up Patronus with @vercel/otel, create an instrumentation.ts file that registers OTEL with a BatchSpanProcessor using OTLPTraceExporter. Configure the exporter URL to process.env.OTEL_EXPORTER_OTLP_ENDPOINT and set the x-api-key header to process.env.PATRONUS_API_KEY. Then call registerTelemetry(new LegacyOpenTelemetry()) to enable automatic telemetry capture.

Patronus gRPC alternative to HTTP exporter

If gRPC is needed instead of HTTP, use the @opentelemetry/exporter-trace-otlp-grpc exporter with the endpoint https://otel.patronus.ai:4317.

Give your agent this brain