AI research
Research at ADCO explores how AI systems learn, how we evaluate their behavior, and how people work with them.
The latest from ADCO AI Labs
Analysis from ADCO AI Labs on datasets, evaluation and human feedback.
A useful dataset is a maintained system.
The value of a dataset depends on what a team can explain, reproduce and improve after the first delivery.
Evaluation starts with the decision.
A score becomes useful when it is tied to a specific workflow, a clear acceptance rule and the evidence behind each judgment.
Human feedback needs a disagreement policy.
The useful signal is often in the reasons people disagree. A review process needs a way to preserve and resolve those differences.
ADCO AI Labs
Our artificial intelligence research lab studies how AI systems learn, how their behavior is evaluated, and how people work with them.
Explore ADCO AI LabsResearch and practice
We explore questions in data preparation, evaluation and human oversight that matter to teams building and using AI. Our analysis connects those questions with published research and the methods behind it.