Waze taps Gemini AI to let drivers chat their way through navigation and customization

Waze, Google's flagship navigation platform, is expanding its feature set with a suite of AI-driven tools designed to streamline how drivers find routes and share road intelligence. The updates reflect a strategic effort to deepen the app's machine learning integration while enhancing user choice around how directions appear.

Smarter Route Suggestions Powered by Your Habits#

The app now recommends routes by analyzing both your individual driving history and broader traffic dynamics in each city. Users who consistently favour highways over residential streets, for instance, will see those options surfaced first—though riders retain full control, with the ability to toggle personalization off entirely or select alternate paths on the fly. The feature is now available worldwide on both Android and iOS.

Conversational Destination Search with Gemini#

Rather than typing specific addresses, users can now ask Waze in natural language to locate what they need. Tapping the voice search icon lets you make queries like "Find me a coffee shop that's open right now," "Find me parking close to Grand Mall," or "Find me a gas station nearby with the lowest prices." The app then presents a curated list of matching locations. This capability is rolling out to beta users globally on both platforms.

Specialized Routing for Motorcycle Riders#

A newly announced Motorcycle mode applies AI reasoning to routes specific to two-wheelers, accounting for shortcuts, legal restrictions, and hazards that matter most to riders. The mode alerts to conditions like potholes, speed bumps, raised crosswalks, and narrow passages while calculating more realistic arrival times. Initial availability spans Argentina, Brazil, Colombia, Malaysia, Mexico, Peru, and the Philippines on both Android and iOS, with further expansion planned.

Crowd-Sourced Map Corrections in Plain Speech#

Building on its existing voice-report system for traffic incidents, Waze now lets users flag map inaccuracies—closed roads, incorrect addresses—by simply speaking them aloud. Statements like "The road is closed here" are relayed to local map editors for verification and correction. This feature launches globally immediately.