Need
What this desk is for.
The author grading the agent they wrote.
Tools · Governance · 29 of 37
1–5 scores. Mean and disagreement.
Need
The author grading the agent they wrote.
How
1–5 scores. Mean and disagreement.
Role analog: AI Trainer and Evaluator · 2026 US year-1 replacement $181,300 (market, not payroll). Kernel runs here. This tab stays local. Not zg, not SignalR, not Copilot, not tiktoken.
Desks that sit this analog: AI Trainer and Evaluator. Unique pain, not a shared slogan.
Second annotator: open this page in another tab. Channel engos.tools.eval.
Governance cluster