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

signoz/options

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.

SigNoz telemetry: control input and output recording

By default, both input values and output values are recorded in telemetry. You can disable input recording by setting telemetry.recordInputs to false, and disable output recording by setting telemetry.recordOutputs to false. This can be useful for privacy, data transfer, and performance reasons.

SigNoz telemetry: add custom metadata with functionId and context

You can add custom metadata to telemetry data by providing a functionId to identify the function and a context object with custom key-value pairs. The functionId is specified in the telemetry option, and context is a top-level option in the generateText call.

SigNoz telemetry: custom Tracer with custom TracerProvider

Instead of using the default TracerProvider from @opentelemetry/api singleton, you can pass a custom Tracer to the LegacyOpenTelemetry constructor. Create a custom TracerProvider, call getTracer() on it to obtain a tracer, and pass it to LegacyOpenTelemetry via the tracer option.

SigNoz custom Tracer example

Example of using a custom Tracer with LegacyOpenTelemetry: import { registerTelemetry, generateText } from 'ai'; import { LegacyOpenTelemetry } from '@ai-sdk/otel'; const tracerProvider = new NodeTracerProvider(); registerTelemetry( new LegacyOpenTelemetry({ tracer: tracerProvider.getTracer('ai'), }), ); const result = await generateText({ model: openai('gpt-5-mini'), prompt: 'Write a short story about a cat.', });

Give your agent this brain