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

Summary

In March 2023, an effort to reduce repetitive questions overwhelming Grab’s ML Platform support channels began as a chatbot for platform documentation and became GrabGPT, an internal ChatGPT-like tool. The initial chatbot used chatbot-ui and more than 20,000 words of Q&A documentation, but GPT-3.5-turbo’s 8,000-token limit forced summaries below 800 words; embedding search also performed poorly, so the approach was abandoned. The pivot extended existing frameworks, added Google login, and deployed a tool through Grab’s catwalk model-serving platform, later named GrabGPT. It reached 300 registered users on day one, more than 3,000 users and 600 daily active users by month three, and nearly all Grabbers according to the post, with private routing, global accessibility, multi-provider model support, and auditable interactions cited as reasons for adoption.

Takeaways

1. 1

   The first chatbot relied on more than 20,000 words of Q&A documentation, but GPT-3.5-turbo’s 8,000-token limit required reducing the material to under 800 words, limiting its usefulness.

2. 2

   GrabGPT grew from 300 registered users on day one to more than 3,000 users and 600 daily active users by month three.

3. 3

   Private routing, global accessibility, support for OpenAI, Claude, Gemini, and other models, and auditable interactions were identified as central to GrabGPT’s adoption.