How OpenTelemetry observes AI agents without code changes

说明与用途

OpenTelemetry eBPF Instrumentation（OBI）实现了对 AI 代理流量的零代码观测，提供一致的遥测数据和因果诊断。

问题

AI agents generate dynamic request paths that traditional request metrics miss, making it hard to attribute token usage and tool calls to specific agents, especially when SDK instrumentation is absent or fragmented.

结果

OBI enables observation of AI agent traffic without code changes, providing consistent telemetry across languages and providers. When combined with a causal model, it allows teams to diagnose performance issues and attribute token usage to specific agents.

工作流

• Deploy OBI as a DaemonSet on the cluster running the agents.
• Configure OBI to capture OpenAI, Anthropic, Gemini, Bedrock, Qwen, MCP over JSON‑RPC, embeddings, and rerank providers.
• Collect consistent telemetry using GenAI semantic conventions.
• Integrate OBI data with existing metrics, logs, and traces.
• Apply Causely’s causal model to match observed symptoms with known cause signatures.
• Review diagnoses to identify and address agent or infrastructure failures.

证据

OBI attaches kprobes and uprobes in the kernel and parses protocols in a separate process outside your application.

来源

One customer's token usage on AWS Bedrock and OpenAI grew 320% in a month, and the team could not tell which agent drove it.

来源

As of OBI v0.9.0, coverage includes OpenAI, Anthropic, Gemini, Bedrock, Qwen, MCP over JSON‑RPC, and embedding and rerank providers.

来源