Skip to content

Evaluation studies, original analysis, and attributed reading on AI evaluation.

33 publications

Evaluation study

Vision segmentation under simulated fog

InspecSpider inspects structures at height. Tests with simulated fog exposed weaknesses in the vision model's segmentation, despite otherwise stable performance.

Model robustness

Evaluation study

An eight-week evaluation of inventory forecasts

A growing bar wanted to replace manual forecasts with AI. It used Knotest to check whether the system could improve stock planning with its own sales data.

Evaluation & assurance

Evaluation study

Comparing AI and manual document processing

An Asian food-and-beverage group spent too much time processing supplier documents by hand. It used Knotest to assess an AI provider before committing to the system.

Evaluation & assurance