Snowflake Observe to add Agent Observability for tracing LLM agents
InfoQ 中文 reports that Snowflake Observe is preparing an Agent Observability feature, planned for private preview, with a launch event scheduled for October 22. The feature is described as capturing prompts, model outputs, retrievals, tool calls, token usage and session IDs through an optional OpenTelemetry-compatible SDK, alongside an Agent Explorer for searching and debugging conversations and metrics covering latency, errors, token use and estimated cost. Snowflake says Observe is built natively on its platform to retain and query large volumes of agent telemetry economically, and it supports online LLM-as-judge evaluations on production traffic.
The article says agent traces are longer and span-heavier than traditional application requests, so rising telemetry retention costs push teams to sample or discard data, leaving gaps when they investigate problems.

2026 年,智能体将在企业级应用中取得哪些实质性突破?点击下载"《2026 年 AI 与数据发展预测》白皮书,获悉专家一手前瞻,抢先拥抱新的工作方式!
AI 智能体正在改变可观测性领域的格局,同时也带来了响应质量和 AI 支出方面的新挑战。即使智能体在执行请求时没有出现错误,仍可能检索到错误的信息,或生成质量不佳的响应。多步骤工作流可能涉及多次提示词输入、工具调用、信息检索、重试和模型生成,因此很难确定质量从哪个环节开始下降,以及哪些因素推动了 Token 消耗和成本增长。此外,智能体产生的遥测数据比传统应用请求更多,进一步增加了保留调查所需数据的成本和复杂性。为了控制成本,团队往往不得不对遥测数据进行采样或直接丢弃部分数据,导致最需要这些数据进行问题排查时,反而面临信息缺失。
#Snowflake#Observe#OpenTelemetry#LangChain#Anthropic Agents SDK#OpenAI Agents SDK