Almost two dozen Democrats on the House Transportation and Infrastructure Committee have asked the Government Accountability Office (GAO) to review the Federal Aviation Administration’s (FAA) use of AI in air traffic tools, according to an October 14 Nextgov report.

They want GAO to examine the FAA’s safety-risk management, performance metrics and deployment strategy for two systems. One is the Strategic Management of Airspace, Routes and Trajectories (SMART) tool, which began limited use on September 21 in the Washington, D.C., region. The other is the Flow Management Data and Services (FMDS) program.

The lawmakers are concerned that AI could produce inaccurate safety-critical information or interfere with decisions made by experienced air traffic controllers, according to Nextgov.

SMART combines about 200 data streams, including weather, flight paths, traffic flow and controller staffing, to give FAA personnel a consolidated view of airspace conditions and recommendations for managing traffic. 

FMDS is meant to replace the agency’s current traffic-flow management system as part of its broader modernization effort.

AI Oversight Moves Beyond Model Performance

The request highlights a broader challenge for agencies deploying AI in high-consequence environments. A system can draw on many data sources, yet its reliability depends on the quality and consistency of those inputs.

For chief data officers (CDOs), that makes data governance part of AI oversight. Agencies need to understand which data feeds inform an AI system, how those inputs are validated and how errors or changes in underlying data could affect its recommendations.

The review also highlights why AI governance in high-stakes environments needs to account for more than model performance. Data lineage, quality controls, validation and monitoring can all affect whether AI-generated recommendations can be trusted.