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

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.

Related reading

• Grab · Jun 20, 2025

  Counter Service: How we rewrote it in Rust

  The Integrity Data Platform team rewrote Counter Service, a high-throughput Golang microservice serving event counts for fraud rules and machine learning models, to evaluate the operational return on investment of Rust. Rather than performing a line-by-line translation, engineers approached the service as a black box, reimplementing core application logic from scratch to satisfy established gRPC contracts across Scylla and Redis. The team resolved internal Go tooling dependencies by building custom configuration template parsers using the nom parser combinator and selected targeted open-source crates such as fred.rs and Cadence. Adapting to Rust required navigating cooperative, stackless async execution compared to Go's preemptive concurrency model, alongside managing borrow checker constraints. Ultimately, the rewrite achieved a 70% reduction in infrastructure costs while maintaining comparable service performance.

  Jia Long Loh

• Grab · Nov 6, 2025

  Grab's Mac Cloud Exit supercharges macOS CI/CD

  Scaling iOS CI/CD workloads across multiple large mobile applications led to substantial expenses and queue delays under rented cloud macOS infrastructure. To mitigate network latency to Git servers and cut compute overhead, Grab relocated its build fleet from a US cloud provider to a colocation data center in Malaysia. The infrastructure deployment relies on over 200 bare-metal Mac minis across 42RU racks, purposefully avoiding virtualization solutions that introduced performance and stability penalties. Phased migration and guardrail monitoring verified cluster stability while achieving 20% to 40% reductions in pipeline and app build times. Operating the regional bare-metal cluster over an estimated three-year hardware replacement lifecycle is projected to yield 2.4 million USD in total cost of ownership savings.

  Madushan Gamage

• Grab · Oct 21, 2025

  Modernising Grab’s model serving platform with NVIDIA Triton Inference Server

  Grab's machine learning serving platform, Catwalk, experienced mounting technical debt, elevated latency, and rising costs from maintaining disparate inference engines for various frameworks. To address these limitations, the team adopted NVIDIA Triton Inference Server to establish a unified engine, starting with an ONNX migration. They built a custom Triton manager component featuring a proxy layer to translate legacy API requests alongside a server manager that handles model downloads, verification, configuration, and health checks. Within ten days, over half of online deployments migrated seamlessly without requiring client code modifications. The transition reduced p90 latency from 120ms to 20ms on large transformer models and cut average infrastructure spend by approximately 20 percent across evaluated services.

  Daniel Tai

• Grab · May 8, 2025

  Streamlining RiskOps with the SOP agent framework

  Manual Account Takeover (ATO) investigations in Risk Operations traditionally demand intensive cross-referencing across systems, manual SQL execution, and high-pressure decision-making prone to human error. To resolve these bottlenecks, an SOP-driven LLM agent framework models investigative workflows as natural-language tree structures with explicit function notations like @function_name. Execution is coordinated between an SOP planner, which traverses the tree using a Depth-First Search strategy, and a Worker Agent that parses JSON-formatted steps to invoke database queries and APIs. Once all steps evaluate their decision criteria, the framework synthesizes the collected data into an actionable summary report. Implementing this architecture automated 87% of ATO cases and dropped average ticket handling time from 22 minutes to 3 minutes.

  Fujiao Liu