# From failure to success: The birth of GrabGPT, Grab’s internal ChatGPT

[Grab](https://yomu.fyi/company/grab) · Wenbo Wei · May 19, 2025

## Summary

Grab's machine learning platform team initially faced overwhelming volumes of repetitive user inquiries across their internal support channels. An initial attempt to automate answers using the open-source chatbot-ui framework and GPT-3.5-turbo failed to scale because the 8,000-token context limit could not accommodate extensive documentation, and embedding search proved inadequate. The project then pivoted to create an internal conversational AI platform called GrabGPT by wiring chatbot-ui with Google authentication and Grab's catwalk model-serving infrastructure. The resulting internal service rapidly expanded across the organization, providing auditable interactions, multi-model support across OpenAI, Claude, and Gemini, and private network routing to safeguard corporate data.

## Takeaways

- Fitting over 20,000 words of documentation into GPT-3.5-turbo was unviable due to its 8,000-token context window, and embedding search was not effective enough for automated platform support.
- GrabGPT was built by combining the open-source chatbot-ui framework, Google authentication, and Grab's internal model-serving platform, catwalk.
- Deploying GrabGPT on private infrastructure enabled full interaction auditing for governance, protected proprietary data, and provided access to employees in regions where commercial ChatGPT is blocked.

**Tags:** [Authentication](https://yomu.fyi/topic/authentication), [LLMs](https://yomu.fyi/topic/llm), [Machine Learning](https://yomu.fyi/topic/machine-learning), [Open Source](https://yomu.fyi/topic/open-source)

[Read original post](https://engineering.grab.com/the-birth-of-grab-gpt)