智能体平台（第一部分）：我们如何帮助 Grab 大规模构建和运行 AI 智能体

Part 1: From one support bot to a framework

第一部分：从一个支持机器人到一个框架

At Grab, AI agents have evolved from interesting team prototypes into production services used every day by millions of merchants, drivers, and consumers. Today, more than 500 services run on our internal agent framework, over 50 Model Context Protocol (MCP) servers are registered on our remote MCP framework, and a single Large Language Model (LLM) gateway fronts every model call across the company, handling billions of tokens each month.

在 Grab，AI 智能体已经从有趣的团队原型发展成为每天被数百万商家、司机和消费者使用的生产服务。如今，有超过 500 个服务运行在我们的内部智能体框架上，超过 50 个模型上下文协议 (MCP) 服务器注册在我们的远程 MCP 框架上，并且一个单一的大型语言模型 (LLM) 网关作为公司内所有模型调用的前端，每月处理数十亿个 token。

None of this was designed up front. It began as the plumbing behind one internal support bot, which then expanded because the same problems kept resurfacing for every team trying to ship an agent. This series tells the story of what the platform eventually became. This Part 1 of the blog focuses on the beginning: the architecture of our AI support bot, the specific pain points we hit while scaling and iterating on it, and how each of those failures became a core building block in the framework we now call LLM-Kit.

这些都不是一开始就设计好的。它最初只是一个内部支持机器人背后的底层管道，后来之所以扩展，是因为每个试图发布智能体的团队都不断遇到相同的问题。本系列讲述了该平台最终演变成的故事。本博客的第 1 部分重点介绍开端：我们的 AI 支持机器人的架构、我们在扩展和迭代它时遇到的具体痛点，以及这些失败中的每一个如何成为我们现在称为 LLM-Kit 的框架中的核心构建块。

The bot that started it

开启这一切的机器人

Imagine you have a question for the Technical Infrastructure (Tech Infra) team - the engineers who run the cloud platforms, databases, developer tooling, and AI infrastructure behind Grab’s ecosystem. Instead of immediately paging an on-call engineer, a bot first triages the request, checks the team’s documentation, runbooks, and past Slack threads, and tries to answer directly in the thread. If it still cannot resolve the issue, it routes the ticket to the right human, with the relevant context already attached.

假设你有一个问题要问技术基础设施 (Tech Infra) 团队——这些工程师负责运行 Grab 生态系统背后的云平台、数据库、开发者工具和 AI 基础设施。机器人不会立即呼叫值班工程师，而是首先对请求进行分类，检查团队的文档、操作...