Zee
Overview
An aviation-specific AI foundation model built as a unified aviation-intelligence platform, trained on real-world operational data - ADS-B feeds from a global network of 6,000+ receivers, ATC communications, maps and charts, aircraft state, terrain, and weather. Designed to run offline/on-device as well as server-hosted, with target applications spanning airline operations, airspace management, UAV/autonomous-flight support, and pilot copilot assistance.
Announced July 15, 2026 as a key pillar of Archer's 'Physical AI' strategy. Built by an approximately 100-person AI team led by Mario Srouji (joined Archer in 2025 from Apple) and advised by Ruslan Salakhutdinov (former VP of AI Research at Meta and Director of AI Research at Apple). On August 5, 2026 Archer said Zee achieved a 'frontier breakthrough' demonstrating real-time prediction of aircraft trajectories on the airport surface several minutes ahead, using a generative conditional-flow-matching framework paired with a satellite-imagery vision transformer; testing has begun at Hawthorne Airport. Archer is in discussions to deploy Zee through pilot programs with governments, airlines, and other industry partners; no commercial deployment had been announced as of early August 2026.