The AI technology that gives Grab’s copywriting tool Mystique its voice

When Grab’s creative teams craft messages for our users and partners they can rely on Mystique, our powerful, in-house copywriting tool.

Mystique spits out highly personalised content for different channels—including in-app messages, push notifications, and emails—in different languages, for different scenarios, all in the Grab voice.

(Also read: Meet Mystique, the AI-powered copywriting tool that helps Grab communicate effectively)

Mystique’s ability to generate personalised content at scale is driven by a sophisticated blend of AI technologies. These include Machine Learning models (ML) which help us predict the user segment an individual belongs to; Large Language Models (LLMs)—these are good at generating creative copy; and Retrieval-Augmented Generation (RAG)—a technique for enhancing the accuracy and reliability of Mystique’s output.

Here’s a closer look at the technical foundation that makes Mystique a gamechanger for content creation at Grab.

Understanding user preferences

The first step required us to understand and segment the different types of user groups on our platform, along with their behaviours, preferences, and engagement patterns.

Grab’s Marketing Analytics team meticulously developed distinct personas and lifecycles based on our proprietary data, gathered from the activities of millions of Grab users and partners across the region.

The Marketing Analytics team developed a comprehensive feature bank, which allows us to apply machine learning models to classify and predict which user group a specific individual is most likely to fall into.

With this methodology, we are able to make data-driven assumptions about the needs and desires of each individual, based on the behaviours of the group, or persona, they most closely resemble—possibly a student looking for affordable meal options, or a parent seeking kid-friendly deals, or an office worker needing a quick lunch solution.

We also understand which part of the lifecycle the individual is in. Are they new to Grab, or a long-term loyal user? Have they interacted with a certain new feature before, or never?

Mystique uses the rich insights embedded in our user persona and lifecycle data to create messages that are highly relevant to each segment.

How Mystique leverages user lifecycles and personas

Let’s demonstrate how that works with a simple example by looking at Grab’s communications for Saver Delivery. (This is an option for users who don’t mind waiting longer for their food delivery, if it costs less.)

Mystique tailors messages based on the consumer’s lifecycle stage, or previous engagement with Saver Delivery, creating distinct messages for those who have used Saver Delivery before, those who haven’t, and those who have stopped. 

Nudging users towards an action, like trying out Saver Delivery if they’ve never done it before, becomes easier if our messages are on point and meet them exactly where they are in their engagement with the feature.

Step 6: We track content performance using metrics like clickthrough rates and open rates. These insights are then fed back into the database where we can retrieve them to enhance future content.