AI Robustness Method
• Collection
Publisher
Software Engineering Institute
Topic or Tag
Abstract
This collection contains artifacts related to the SEI LTP project to transition the AI Robustness (AIR) method.
Collection Items
AI Robustness (AIR) Tool
• Software
By Michael D. Konrad, David James Shepard, Nicholas Testa
The AI Robustness (AIR) tool allows users to gauge AI/ML classifier performance with unprecedented confidence.
Download
AI Robustness (AIR)
• Presentation
By Linda Parker Gates, Nicholas Testa
Linda Parker Gates and Dr. Nicholas Testa presented this project at the CMU SEI Research Review 2024.
Learn More
Gain Greater Confidence in Your AI Solutions with AIR: Using Causal Discovery, Identification, and Estimation to Improve Your AI Classifiers
• Presentation
By Linda Parker Gates, Nicholas Testa
Linda Parker Gates and Dr. Nicholas Testa presented this poster at Research Review 2024.
Learn More
Getting Started with AIR
• Brochure
By Software Engineering Institute
Learn the benefits of being an Artificial Intelligence Robustness (AIR) partner at the SEI.
Learn More
SEI Tool Helps Determine Causes of AI Bias, Improves AI Trust
• Newsletter
By Software Engineering Institute
This SEI Bulletin newsletter was published on July 23, 2025.
Read
Can You Rely on Your AI? Applying the AIR Tool to Improve Classifier Performance
• Webcast
By Linda Parker Gates, Crisanne Nolan, Michael D. Konrad, Suzanne Miller, Nicholas Testa, David James Shepard
In this webcast, SEI researchers discuss a new AI Robustness (AIR) tool that allows users to gauge AI and ML classifier performance with confidence.
Watch
SEI Tool Helps Determine Causes of AI Bias, Improves AI Trust
• News Item
By Software Engineering Institute
With the increasing use of AI classifiers in the Department of Defense and across the federal government to make classifications and predictions in operations, mission planning, simulation, logistics, and threat …
Read
From Data to Performance: Understanding and Improving Your AI Model
• Podcast
By Linda Parker Gates, Nicholas Testa, Crisanne Nolan
In this podcast, SEI researchers discuss the AI Robustness (AIR) tool, which allows users to gauge AI and ML classifier performance with data-based confidence.
Listen
Applying Causal Learning to Evaluate Large Language Models (LLMs)
• SEI Report
By Michael D. Konrad, Andrew O. Mellinger, Linda Parker Gates, David James Shepard, Nicholas Testa
This report describes how the SEI applied causal discovery to LLM summarization, exemplifying a way to address bias when evaluating complex new technology.
Read