Kolab measured 115 hours of real work and found agents need humans

Kolab is a test suite built from over 115 hours of screen recordings of real knowledge workers doing real tasks. Researchers captured when those workers stopped, redirected, or corrected the work in progress. Most existing test suites measure agents working alone from start to finish. Kolab shows that real work does not look like that. The recordings reveal a pattern: humans step in, check progress, and change direction at key moments. The test suite treats those moments as first-class events, not interruptions to be designed out. A product team that trains or tests an agent on solo runs will miss the behaviors that matter most in a professional setting. For designers, the core finding is structural. The right question is whether a human and an agent can finish a task together. Kolab gives teams a way to measure that. It names the check-ins, the redirections, and the correction steps as measurable parts of quality, not noise.