[{"data":1,"prerenderedAt":15},["ShallowReactive",2],{"explorations":3},[4],{"path":5,"title":6,"description":7,"date":8,"tags":9,"status":13,"icon":14},"\u002Fexplorations\u002Fmaestro-bench","MAESTRO-bench, comparing AI agents","How a benchmark tool for AI agents went from scripts and CSV files to a loop of dataset, experiment and analysis, grouped in studies.","2026-10-22",[10,11,12],"AI","Benchmark","Workflow","wip","lucide:flask-conical",1792744397093]