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

respan/capabilities

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.

Enable telemetry in generateText with Respan

To capture traces with Respan, pass experimental_telemetry with isEnabled set to true in the generateText call.

Enable telemetry code example with generateText

import { openai } from '@ai-sdk/openai'; import { generateText } from 'ai'; const result = await generateText({ model: openai('gpt-4o-mini'), prompt: 'Tell me a joke about AI', experimental_telemetry: { isEnabled: true }, });

Respan tracing capabilities

Respan captures tracing data for each AI SDK call including input, output, token usage, cost, and latency. It also captures tool calls and structured output.

Respan gateway supports 250+ models

Respan's gateway routing integrates with over 250 models behind a single endpoint, enabling unified access across different model providers.

Give your agent this brain