AI & Technology

Bitdrift AI powers agentic mobile observability across hundreds of millions of devices

A mobile observability startup founded by former Lyft engineers has launched a new product aimed at helping AI agents investigate and resolve app issues in real time.

bitdrift, which says its software is installed more than a billion times across hundreds of millions of devices worldwide, today introduced bitdrift AI, a system that gives AI agents access to full-resolution mobile telemetry without sampling.

From the beginning, the bitdrift platform has been designed to help enterprises detect, diagnose, and fix problems faster, especially in complex mobile environments where network conditions, device variability, and UI changes can obscure the source of issues.

The launch of bitdrift AI comes as software teams increasingly experiment with agentic tools that can take action autonomously. According to bitdrift CEO Peter Morelli, those systems are only as effective as the data they can access.

Agentic AI has changed software engineering, but agents can only be as smart as the data they see,” Morelli said. He argues that traditional observability tools weren’t built for mobile apps running in less predictable conditions. “bitdrift AI is the first solution that gives AI agents direct access to full-resolution mobile data, without sampling.”

The company says its platform captures logs, traces, and session context directly on device, then streams that information to its control plane in real time. Through a CLI, public API, and customized skills, teams can query devices, inspect issues, and create instrumentation without waiting for a new app release.

bitdrift also says their system can narrow the data collected through local capture buffers and server-controlled targeting, a design intended to reduce noise and preserve model context windows for AI agents.

The startup’s founding team includes engineers with mobile infrastructure experience at Twitter and Lyft. bitdrift says that background shaped a platform built to handle billions of installs and the inconsistencies of real-world devices.

Valerii Kuznietsov, senior staff software engineer and mobile engineering lead at ThredUp, said the product has changed how his team handles customer issues. “With bitdrift, we’ve brought infinite scale to problem resolution,” he said. “Because we have enough data and AI to help us, we can help 90-95% of customers experiencing minor problems instead of the 20-30% that we could support before.”

The company has raised $15 million from investors including Amplify Partners, 01 Advisors, Primeset, and Lyft.

Author:

Related Articles

Back to top button