# Reshaping Chat Support for Our Users

[Grab](https://yomu.fyi/company/grab) · Elisa Monacchi · Jul 7, 2021

**Type:** Problem & solution

## Summary

Grab transitioned from voice hotlines and third-party tools to an in-house native chat support system integrated into their CRM. The team validated the platform through an MVP and user shadowing to address session disconnections, agent context switching, and routing bottlenecks. To optimize support operations at scale, they introduced dynamic queue limits based on Little's law, machine learning autocomplete suggestions for agents, and duration timers with visual nudges. These enhancements reduced chat waiting times by 30%, unresponsive users by 7%, and overall chat handling duration by 22%.

## Context

Grab relied on voice hotlines and disjointed support tools where queue times were long, issue descriptions were difficult, and third-party chat tools suffered from frequent disconnections.

## Approach / What changed

Grab built a native in-app chat platform integrated with their internal CRM and data, deploying dynamic queue limits using Little's law, machine learning autocomplete for agents, and visual duration timers.

## Takeaways

- Applying Little's law to establish dynamic queue limits reduced chat waiting time by approximately 30% and lowered unresponsive user rates by roughly 7%.
- Introducing a machine learning autocomplete tool based on user type, entry point, and conversation context reduced average chat time by 12%.
- Adding color-coded duration timers and visual nudges to agent chat windows helped reduce average chat time by 22%.

**Tags:** [Architecture](https://yomu.fyi/topic/architecture), [Machine Learning](https://yomu.fyi/topic/machine-learning)

[Read original post](https://engineering.grab.com/reshaping-chat-support)