Four ways Grab solves real-world user challenges with AI

Grab Editorial

. January 13, 2026 . Regional

At Grab, artificial intelligence (AI) is a key driver behind much of how we innovate and transform how consumers interact with everyday services on our platform.

The following four examples demonstrate how our AI technology solves real-world challenges for our users:

Solving navigation friction with visual pickup guides

Getting to pickup points can be difficult for passengers who find themselves in unfamiliar areas, such as busy malls or large airports.

We’ve created video walkthroughs that serve as guides to these pickup points. We do this by making use of existing visual data and AI tools that can stitch together static photos into an immersive walk-through video experience, minimising the need for manual video production. That means we can quickly roll out video guides for more locations.

These video guides reduce confusion, minimise waiting times, and prevent unnecessary cancellations, ensuring passengers connect with your driver quickly and efficiently.

Overcoming language barriers with accurate local menu translations

Ordering from local merchants shouldn’t be hindered by language barriers. Our AI models are specifically trained on regional food terms to ensure highly accurate translations that generic tools often miss. This allows consumers to explore and order from local eateries in their preferred language.

Making ride booking accessible with LLMs and voice recognition

Our AI Voice Assistant allows visually impaired users to simply speak their intent and get going: faster, easier, and with more independence.

The feature uses large language models and voice recognition to interact with users through voice commands. It guides users through the process of booking a ride and keeps users updated on the driver’s status, from the moment a driver is found to their arrival.

Ensuring delivery reliability for large orders with automated order splitting

Delivering large food or grocery orders can be a logistical challenge for our delivery-partners, especially those on motorcycles. To improve the reliability of large order deliveries, Grab has introduced a system to split bulky orders across two delivery-partners at no extra cost to the customer.

This is done by a system-initiated split where a Large Language Model evaluates orders based on size and weight. Meanwhile, delivery-partners can also initiate splits if they find an order too large to handle alone, even if not flagged by the system.

This ensures that consumers enjoy faster and more reliable delivery for every occasion.

Solutions