Academic survey: How do people use and debug AI agents for multi-step tasks?

Hi everyone,

I’m running a short academic survey about how people use chat-based AI agents for multi-step tasks, and how this compares with reusing or editing workflow-style automations.

The survey asks about your experience with AI agents, how you check or debug their results, and when you would prefer editing a visible workflow versus asking an AI agent to complete a similar task from scratch.

It should take about 5–10 minutes. There are no right or wrong answers; I’m interested in real experiences and preferences from people who work with automation, workflows, or AI agents. Participants can optionally leave an email address to be considered for a €10 Amazon eGift card.

Survey link

Thanks a lot for your help!