Setup Sentry AI Agent Monitoring

Configure Sentry to track LLM calls, agent executions, tool usage, and token consumption.

Invoke This Skill When

• User asks to "monitor AI/LLM calls" or "track OpenAI/Anthropic usage"
• User wants "AI observability" or "agent monitoring"
• User asks about token usage, model latency, or AI costs

Prerequisites

AI monitoring requires tracing enabled (tracesSampleRate > 0).

Detection First

Always detect installed AI SDKs before configuring:

# JavaScript
grep -E '"(openai|@anthropic-ai/sdk|ai|@langchain|@google/genai)"' package.json

# Python
grep -E '(openai|anthropic|langchain|huggingface)' requirements.txt pyproject.toml 2>/dev/null

Supported SDKs

JavaScript

*Vercel AI requires explicit setup for Edge runtime and experimental_telemetry per-call.

Python

JavaScript Configuration

Auto-enabled integrations (OpenAI, Anthropic, Google GenAI, LangChain)

Just ensure tracing is enabled. To capture prompts/outputs:

Sentry.init({
  dsn: "YOUR_DSN",
  tracesSampleRate: 1.0,
  integrations: [
    Sentry.openAIIntegration({ recordInputs: true, recordOutputs: true }),
  ],
});

Next.js OpenAI (additional step required)

For Next.js projects using OpenAI, you must wrap the client:

import OpenAI from "openai";
import * as Sentry from "@sentry/nextjs";

const openai = Sentry.instrumentOpenAiClient(new OpenAI());
// Use 'openai' client as normal

LangChain / LangGraph (explicit)

integrations: [
  Sentry.langChainIntegration({ recordInputs: true, recordOutputs: true }),
  Sentry.langGraphIntegration({ recordInputs: true, recordOutputs: true }),
],

Vercel AI SDK

Add to sentry.edge.config.ts for Edge runtime:

integrations: [Sentry.vercelAIIntegration()],

Enable telemetry per-call:

await generateText({
  model: openai("gpt-4o"),
  prompt: "Hello",
  experimental_telemetry: { isEnabled: true, recordInputs: true, recordOutputs: true },
});

Python Configuration

import sentry_sdk
from sentry_sdk.integrations.openai import OpenAIIntegration  # or anthropic, langchain

sentry_sdk.init(
    dsn="YOUR_DSN",
    traces_sample_rate=1.0,
    send_default_pii=True,  # Required for prompt capture
    integrations=[OpenAIIntegration(include_prompts=True)],
)

Manual Instrumentation

Use when no supported SDK is detected.

Span Types

Example (JavaScript)

await Sentry.startSpan({
  op: "gen_ai.request",
  name: "LLM request gpt-4o",
  attributes: { "gen_ai.request.model": "gpt-4o" },
}, async (span) => {
  span.setAttribute("gen_ai.request.messages", JSON.stringify(messages));
  const result = await llmClient.complete(prompt);
  span.setAttribute("gen_ai.usage.input_tokens", result.inputTokens);
  span.setAttribute("gen_ai.usage.output_tokens", result.outputTokens);
  return result;
});

Key Attributes

PII Considerations

Prompts/outputs are PII. To capture:

• JS: recordInputs: true, recordOutputs: true per-integration
• Python: include_prompts=True + send_default_pii=True

Troubleshooting