Scores whether an ATS can actually read your resume, then rewrites it. The audit is deterministic, runs offline with no API key, and is itself benchmarked at 1.00 precision and recall against resumes with planted defects.
Get noisy agents to a better answer than any one of them. Panel voting is a real 20+pt jump; found the extra '+1pt from debate' claim doesn't survive proper statistical power (20 trials wasn't enough, true effect is ~0).