Amazon is entering the custom silicon game in a serious way. In a wide-ranging interview on CNBC's "The Tech Download" podcast, Amazon's head of devices and services Panos Panay revealed for the first time that the company is designing its own end-to-end chips for its most critical consumer hardware.
"We do make our own end-to-end silicon for the devices that we ship," Panay said, confirming that Amazon's custom chips are already inside products like the Echo Show 8, Echo Show 11, and Fire TV. The executive explained that tight hardware-software integration is essential for delivering the kind of ambient, secure AI experiences Amazon envisions for the home.
In October 2025, Amazon unveiled the AZ3 and AZ3 Pro chips, designed specifically to run AI models on-device rather than in the cloud. This approach — known as on-device or edge AI — offers significant advantages: faster response times since data doesn't need to travel to remote servers, improved privacy as personal data stays on the device, and the ability to function without an internet connection.
The custom silicon push mirrors strategies already employed by Apple, which designs its own A-series and M-series chips, and increasingly by Google with its Tensor chips. For Amazon, the move is closely tied to the rollout of Alexa+, the upgraded version of its digital assistant that can handle more complex queries, learn user patterns, and tie together the company's sprawling ecosystem of devices — from Ring doorbells to Echo speakers to Fire TV.
Panay also hinted at ambitious future hardware, describing a "whole roadmap of on-the-go devices" — gadgets people carry with them that collect data and respond to voice. Amazon acquired wearable startup Bee last year, which makes $49.99 wristbands capable of voice interaction. "You won't have to wait long" for an Amazon mobile product, Panay said.
He noted that while Amazon is investing heavily in custom silicon, it continues to use chips from partners like Qualcomm for certain products. The hybrid approach allows the company to optimize performance where it matters most while maintaining flexibility across its vast product lineup.
The broader context: as AI moves beyond screens and apps into ambient computing, the battle for the home is intensifying. Amazon faces stiff competition from Google (with Gemini and Android), Apple, and Samsung, all racing to define how consumers interact with AI in daily life. Custom chips give Amazon tighter control over the user experience, potentially creating a moat around its ecosystem.
