AI Agent Tester - Real-World Tasks

About the Role

AI agents are starting to handle real-life errands such as paying bills, booking trips and doing the groceries. This contractor project measures how well they actually perform from a real user's point of view, with two agents tested side by side on your own phone and accounts.

What You'll Do

• Run real-life scenarios: bills, returns, email follow-ups, bookings, shopping, groceries, travel, family logistics, outings and forms
• Approve or stop the agent at key steps
• Screen record every attempt
• Score each run on completion, quality, control issues, satisfaction and time
• Write clear feedback on the agent experience

Requirements

• US-based, with a Bachelor's degree
• Already uses AI in daily life; 2-3 years of experience, preferably in engineering, business management or office/operations
• Detail-oriented, good at following instructions and documenting each step; clear written communication
• An active paid-tier (Plus) personal AI assistant account, active Muse and Dots access, a smartphone that can screen record, and a payment card for test purchases (reimbursed afterward)
• No coding or AI background needed; generalists welcome, domain experts preferred

Compensation & Logistics

Pay is $25-$45 per hour as a contractor, with roughly 1.5 hours per run including evidence and scoring. The project is already active. Onboarding follows within 24-48 hours of selection, and work is done entirely from your phone on your own schedule. Location: US-based. Selection: apply and answer the screening questions, then a role-specific AI interview where required, a profile review and onboarding with the Talent Ops team. The interview takes 15-30 minutes.