AI Pillar Hub

whatbroke

Compare agent runs to identify changes in behavior, cost, and results.

A command-line tool for comparing agent executions, including tool usage, arguments, expenses, timing, and results.

Pricing label: see the product site.

Open whatbroke

Is this your tool? Feature it

More in this area

AI Prompts & Eng

AceTagGen

Build and score structured prompts for Suno music generation.

See siteVisit

AI Prompts & Eng

ai-evaluation

Evaluate AI workflows with metrics, judges, scanners, and CI pipelines.

See siteVisit