Snyk 把内部支持智能体做成客户功能
LangChain 博客发文介绍 Snyk 如何将内部客服智能体发展为面向客户的产品 Snyk Assist。该智能体基于 LangChain 与 LangGraph 构建，用 LangSmith 做可观测与评估，能查未解决问题、检查软件包漏洞、在对话中开支持工单或提交功能请求。文章称它先在内部用于工单分诊约一年，2026 年 4 月进入支持门户，9 月 1 日移入 Snyk 核心产品，成为每个付费客户可见的顶栏面板。Snyk 表示自 4 月上线以来已处理逾 6 万次查询、覆盖 500 多个客户账户，85% 以上会话无需开单即获解决，这些均为其自报数据。
Snyk 把权限控制与 LangSmith 评估作为上线前提：工具按登录用户权限在请求时挂载，每次变更需通过评估阈值才能发布，这展示了安全类产品上线智能体时的做法。
Key Takeaways
- We started with a real customer pain point. Snyk Assist was built to make it easier for customers to get fast, accurate answers without having to search across docs, support content, and account systems.
- We treated trust and access control as core product requirements. Because Snyk is a security platform, the agent was designed to stay within a user’s permissions and to prove it was safe, reliable, and correct before broader rollout.
- We built it to be useful, measurable, and scalable. A single LangGraph runtime powers multiple surfaces, while LangSmith evaluations help the team catch regressions, improve responses, and keep shipping with confidence.
Snyk is an AI Security Platform. Its platform finds and fixes vulnerabilities in code, open source dependencies, containers and cloud configuration, and they sit inside the places developers already work: the IDE, the pull request, and the pipeline.
We build security products for developers, which means our customers ask hard, specific questions. They want answers about vulnerabilities, account context, support issues and product behavior, often in the middle of real work. Before Snyk Assist, this information was spread across product documentation, support articles, release notes, learning content and account data. Finding the right one usually meant reading several pages or filing a ticket and waiting.