You will evaluate how two AI agents handle everyday errands and digital tasks from a user's point of view. You will test them side by side on a smartphone, make decisions at key checkpoints, and document the results.
You will provide evidence and feedback that helps improve how AI agents handle practical activities such as payments, bookings, shopping, communication, and forms.
- Run scenarios involving bills, returns, email follow-ups, bookings, shopping, groceries, travel, family logistics, outings, and forms.
- Approve or stop an AI agent at important steps during each task.
- Capture a screen recording of every attempt with a smartphone.
- Score completion, quality, control issues, satisfaction, and time for each run.
- Write clear feedback about what worked, what failed, and how the interaction felt.
- Some tests may involve personal AI accounts and real purchases with your own card. Reimbursement is provided afterward.