Archer Aviation announced Zee, what it describes as the world's leading aviation-specific AI foundation model, trained on real-world operational data and designed to work both offline and as a server-hosted solution across the entire aviation ecosystem. The model integrates automatic dependent surveillance broadcast (ADS-B) signals, air traffic control communications, maps, charts, aircraft state information, terrain data, and weather information into a unified intelligence platform.

What Makes Zee Different From General-Purpose AI Models?

Unlike general-purpose AI models trained on internet text, Zee is purpose-built for aviation. The model was trained on real-world operational data aggregated through Archer's proprietary data pipeline and a global network of over 6,000 ADS-B receivers, which track aircraft positions and transmit that data continuously. This specialized training approach allows Zee to understand the disparate data sources that pilots and air traffic controllers piece together in real time, such as radio calls, navigation inputs, and aircraft state information.

Archer's AI team consists of nearly 100 researchers and engineers led by Mario Srouji, who previously worked at Apple. The team is advised by Professor Ruslan Salakhutdinov, former vice president of AI research at Meta and director of AI research at Apple. This combination of industry expertise and academic guidance positions the company to address aviation-specific challenges that general-purpose models cannot solve.

The key technical advantage of Zee is its ability to run on-device without requiring internet connectivity, a critical requirement for aviation environments where connectivity may be unreliable. The model can also operate as a server-hosted solution, making it flexible for deployment across different operational contexts.

How Could Zee Improve Aviation Safety and Efficiency?

Archer is in discussions to deploy Zee through pilot programs with governments, airlines, and other industry partners. The initial applications include airline operations, airspace management, and copilot assistance, with the stated goal of improving flight safety and efficiency. On a typical day, more than 45,000 flights move through American airspace, generating a constant flow of data that Zee is designed to process and interpret as a unified system.

The timing of Zee's announcement aligns with broader industry recognition that aviation infrastructure needs modernization. The U.S. Department of Transportation has committed approximately $20 billion to modernizing the national airspace system, reflecting the need to upgrade legacy technology that currently manages flight operations.

"We are building an intelligence layer for the entire aviation system with Zee. The company that owns the data and the foundation model will help lead the aviation industry into the next era of flight," said Adam Goldstein, founder and CEO of Archer.

Adam Goldstein, Founder and CEO at Archer Aviation

"Aviation is having its GPT moment. Our current national air system is built on legacy technology, and is ripe for AI innovation. Archer's world-class team, and industry-leading Zee foundation model positions us to help lead the industry transformation; unlocking new levels of safety, efficiency, and scale for America's airspace," stated Mario Srouji, VP of AI Products at Archer.

Mario Srouji, VP of AI Products at Archer Aviation

Ways Zee Could Transform Aviation Operations

• Real-Time Data Integration: Zee processes ADS-B signals, ATC communications, maps, aircraft state, terrain, and weather data simultaneously, allowing operators to understand complex airspace situations faster than manual interpretation.
• On-Device Processing: The model can run locally without internet connectivity, critical for aircraft and ground systems in areas with unreliable or no connectivity, reducing latency and improving reliability.
• Scalable Deployment: Zee can operate both as an on-device solution and as a server-hosted platform, making it adaptable to different aviation environments from air taxis and unmanned aircraft to commercial airlines and air traffic management systems.
• Copilot Assistance: The model can provide decision support to pilots and air traffic controllers, potentially reducing workload and improving situational awareness during complex operations.
• Airspace Modernization Support: Zee is designed to work with the U.S. Department of Transportation's $20 billion modernization initiative, helping transition from legacy systems to AI-enhanced operations.

Archer's announcement of Zee comes as the eVTOL industry continues to mature. While competitors like Joby Aviation, Beta Technologies, and others view autonomous systems as critical to scaling operations beyond a handful of daily flights, Archer is taking a different approach by building an AI foundation model that could serve the entire aviation ecosystem, not just its own aircraft.

The development of Zee also reflects a broader shift in how aviation companies are approaching technology. Rather than focusing solely on aircraft design, Archer is investing in the software and AI systems that will be necessary to integrate electric aircraft into the national airspace system. This positions the company not just as an aircraft manufacturer, but as a provider of aviation intelligence infrastructure.

Archer's strategy with Zee differs from competitors who are pursuing autonomous flight capabilities. For example, Wisk Aero, Boeing's eVTOL unit, recently demonstrated the ability for a single ground-based supervisor to manage multiple uncrewed aircraft simultaneously in simulation with NASA, focusing on autonomous operations at scale. Archer's approach with Zee is broader, targeting the entire aviation system rather than just autonomous flight management.

The company's next steps involve deploying Zee through pilot programs with government agencies, airlines, and industry partners. These pilots will test the model's performance in real-world operational environments and help refine its capabilities before wider commercial deployment. As the aviation industry continues to modernize and integrate new technologies like electric aircraft, AI foundation models like Zee may become essential infrastructure for managing increasingly complex airspace operations.