Agent platform (Part 1): How we help Grab build and run AI agents at scale
Grab's internal AI agent work started as a Tech Infra support bot and grew into a company-wide platform: more than 500 services run on its agent framework (LLM-Kit), over 50 Model Context Protocol servers are registered on its remote MCP framework, and a single LLM gateway fronts every model call across the company, handling billions of tokens each month for production agents used daily by millions of merchants, drivers, and consumers. Part 1 covers how the original Go bot's reasoning plane and tool plane became reusable framework building blocks, and how problems that appeared around 500 agents—shared model control, safe tool reuse across teams, and evals after prompt changes—pushed the team toward the GrabGPT Gateway, remote MCP, and an evals platform covered in later parts.
- Published
- 2026-07-24
- Scale
- 500+ services on the internal agent framework, 50+ remote MCP servers, billions of tokens/month through one LLM gateway, millions of merchants, drivers, and consumers
- Techniques
- agent framework LLM gateway remote MCP tool plane
- Stack
- LLM-Kit GrabGPT Gateway Model Context Protocol Go