207 points118 comments
New benchmark tests AI agents on real tax advice
What is Dayjob: Tax – evaluating AI agents on 50 professional tax assignments?
DAYJOB: Tax offers 50 realistic tax scenarios for AI agents, from filing to advisory decisions. It checks whether the agents spot hidden deadlines and give advice a human tax professional would.
Who it is for
AI developers and tax tech firms can use it to measure and improve their agents' professional judgment.