20192026

Feature trailActive

AI Assistant Routing and Context Management

Grab's AI Assistant for account managers, Jarvis Pro, has evolved with a 'route first, answer later' design. This system classifies user prompts to determine the appropriate task type, scope, and necessary context before generating an answer. This approach aims to prevent common errors by ensuring the system understands the user's intent and loads only relevant information, improving the accuracy and safety of AI-generated recommendations. The post details the router's design, memory management, and evaluation strategies, emphasizing the tradeoff between first token latency and response safety. Regression checks were implemented to reconcile metric discrepancies between reporting surfaces.

1 post · 2026

Timeline

Feature trailActive

AI Agent Framework

Grab's AI Gateway provides a centralized, unified interface for accessing multiple GenAI providers (OpenAI, Azure, AWS Bedrock, Google VertexAI, etc.). It streamlines access, enables experimentation with various LLMs, optimizes cost-efficiency through shared capacity, and enforces auditing and platformization benefits like monitoring, cost attribution, and rate limiting. The architecture acts as a reverse proxy, handling authentication, authorization, and rate limiting, while also supporting div. The LLM-Kit is a comprehensive framework designed to supercharge the setup of production-ready LLM applications, providing a pre-configured structure, integrated tech stack, built-in observability, efficient config and secret management, authentication, API documentation, Redis & vector database integration, a deployment pipeline, and seamless integration with LangSmith for evaluations. It has onboarded hundreds of GenAI applications and is the de facto choice for developers, saving an estimated 1.5 weeks per team before feature development.

3 posts · 2024–2026

Timeline

20242026

Feature trailActive

AI-Assisted Analytics

Grab's AI-Assisted Analytics initiative has evolved with Metasense V2, an LLM-powered system for data governance. This iteration enhances data classification by splitting the model into PII and non-PII taggers, refining prompts for better accuracy with complex data structures, and improving model capacity by reducing tag count and handling large tables. The integration of LangChain and LangSmith frameworks streamlines prompt experimentation, evaluation, and deployment, enabling rapid iteration. The Gemini orchestration service now integrates LLM classification for column-level tagging, addressing challenges with third-party tools and manual classification. It manages requests, aggregates them into batches, and employs rate limiting. The LLM is prompted to act as a column tag classifier, assigning tags based on table and column names, with a defined set of tags and a JSON output format. Techniques like clear articulation of requirements and few-shot learning are used for prompt engineering.

11 posts · 2019–2026

Timeline

20192026

Feature trailActive

Android Studio IDE Performance in Monorepo

Grab has evolved its Android Studio IDE performance by developing a custom Focus plugin. This plugin leverages pre-computed dependency graphs from the Gradle-to-Bazel migration workflow to allow developers to selectively sync only the modules they are actively working on, drastically reducing sync times and memory consumption. The plugin integrates seamlessly with Android Studio via an IntelliJ plugin, providing a user-friendly interface for module selection and dependency visibility, thereby improving developer productivity in large monorepos.

2 posts · 2020–2026

Timeline

20202026

Feature trailActive

Counter Service Storage Migration

Grab's Counter Service has evolved to provide a self-service platform for fraud detection, enabling data scientists and analysts to create and manage counters without direct engineering intervention. The system is designed for high scalability, handling billions of transactions daily by leveraging Aerospike for time-series data storage with a map-based schema for optimized storage and retrieval. This migration focused on decoupling storage concerns from business logic, redesigning the data model, and optimizing performance by removing a Redis cache and relying on Scylla's native caching. This has led to more balanced load and reduced latency during peak hours.

5 posts · 2017–2026

Timeline

20172026

Feature trailActive

Data Lake Modernization with Apache Iceberg

Grab has adopted Apache Iceberg as the foundational table format for its data lake, migrating from Hive Parquet. This transition addresses challenges with catalog latency, the small file problem, operational toil, and data consistency. A key component of this migration is the open-sourced UnifiedSparkCatalog, which provides significant improvements in query performance, reduced S3 API costs, and compute savings. The Talaria time-series database has evolved to use Go plugins for custom data processing.

6 posts · 2017–2026

Timeline

20172026

Feature trailActive

20172026

Feature trailQuiet since 2017

DNS Resolution Behavior

This post investigates and explains the differences in DNS resolution behavior between Go's native resolver, Cgo, and C, particularly concerning RFC 6724 (3484) and IPv6. It details how disabling IPv6 affects IP address sorting and identifies that Go's native resolver implements only a partial subset of RFC 6724 rules, lacking source address selection, which leads to different outcomes compared to Cgo/C resolvers.

1 post · 2017

Timeline

20172026

Feature trailQuiet since 2017

ELB Health Check Monitoring and Debugging

Grab has evolved its understanding and debugging of Elastic Load Balancer (ELB) health check behavior. This post details an investigation into unexpected increases in health check metrics, which were initially mistaken for new instance scaling. The root cause was identified as the coexistence of old and new ELB nodes during scaling events, leading to a doubling of health checks. This led to a refinement in monitoring practices, separating dependency health checks from ELB health checks and emphasizing the importance of understanding the nuances of ELB behavior during scaling events.

2 posts · 2015–2017

Timeline

…20172026

Feature trailQuiet since 2016

API and SDK User Experience

Grab is evolving its approach to API and SDK design by emphasizing User Experience (UX) for both human programmers and other systems. This involves applying UX principles to the design of interfaces, considering factors like usability, efficiency, and developer productivity. The goal is to create more intuitive, robust, and maintainable APIs and SDKs that reduce complexity and improve the overall developer workflow.

1 post · 2016

Timeline

…20172026