Patronus Observability

Patronus AI provides an end-to-end system to evaluate, monitor and improve performance of an LLM system, enabling developers to ship AI products safely and confidently. Learn more here.

When you build with the AI SDK, you can stream OpenTelemetry (OTEL) traces straight into Patronus and pair every generation with rich automatic evaluations.

Setup

1. OpenTelemetry

Patronus exposes a fully‑managed OTEL endpoint. Configure an OTLP exporter to point at it, pass your API key, and you’re done—Patronus will automatically convert LLM spans into prompt/response records you can explore and evaluate.

Environment variables (recommended)

bash

OTEL_EXPORTER_OTLP_ENDPOINT=https://otel.patronus.ai/v1/traces
OTEL_EXPORTER_OTLP_HEADERS="x-api-key:<PATRONUS_API_KEY>"

With `@vercel/otel`

import { registerOTel } from '@vercel/otel';
import { OTLPTraceExporter } from '@opentelemetry/exporter-trace-otlp-http';
import { BatchSpanProcessor } from '@opentelemetry/sdk-trace-node';

export function register() {
  registerOTel({
    serviceName: 'next-app',
    additionalSpanProcessors: [
      new BatchSpanProcessor(
        new OTLPTraceExporter({
          url: process.env.OTEL_EXPORTER_OTLP_ENDPOINT,
          headers: {
            'x-api-key': process.env.PATRONUS_API_KEY!,
          },
        }),
      ),
    ],
  });
}

<Note> If you need gRPC instead of HTTP, swap the exporter for `@opentelemetry/exporter-trace-otlp-grpc` and use `https://otel.patronus.ai:4317`. </Note>

2. Enable telemetry on individual calls

The AI SDK emits a span only when you opt in with experimental_telemetry:

import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await generateText({
  model: openai('gpt-4o'),
  prompt: 'Write a haiku about spring.',
  experimental_telemetry: {
    isEnabled: true,
    functionId: 'spring-haiku', // span name
    metadata: {
      userId: 'user-123', // custom attrs surface in Patronus UI
    },
  },
});

Every attribute inside metadata becomes an OTEL attribute and is indexed by Patronus for filtering.

Example — tracing and automated evaluation

import { trace } from '@opentelemetry/api';
import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';

export async function POST(req: Request) {
  const body = await req.json();
  const tracer = trace.getTracer('next-app');

  return await tracer.startActiveSpan('chat-evaluate', async span => {
    try {
      /* 1️⃣ generate answer */
      const answer = await generateText({
        model: openai('gpt-4o'),
        prompt: body.prompt,
        experimental_telemetry: { isEnabled: true, functionId: 'chat' },
      });

      /* 2️⃣ run Patronus evaluation inside the same trace */
      await fetch('https://api.patronus.ai/v1/evaluate', {
        method: 'POST',
        headers: {
          'X-API-Key': process.env.PATRONUS_API_KEY!,
          'Content-Type': 'application/json',
        },
        body: JSON.stringify({
          evaluators: [
            { evaluator: 'lynx', criteria: 'patronus:hallucination' },
          ],
          evaluated_model_input: body.prompt,
          evaluated_model_output: answer.text,
          trace_id: span.spanContext().traceId,
          span_id: span.spanContext().spanId,
        }),
      });

      return new Response(answer.text);
    } finally {
      span.end();
    }
  });
}

Result: a single trace containing the root HTTP request, the LLM generation span, and your evaluation span—all visible in Patronus with the hallucination score attached.

Once you've traced

If you're tracing an agent, Patronus's AI assistant Percival will assist with error analysis and prompt optimization. Learn more here
Get set up on production monitoring and alerting by viewing logs and traces on Patronus and configuring webhooks for alerting. Learn more here

Patronus