Empty Prompt Box Where New Users Give Up
A new user opens an AI assistant and sees a blank text box with a blinking cursor. Maybe a placeholder says "How can I help?" Nobody told them what it can actually do. They type something vague, get a vague answer, and close the tab. Nielsen Norman Group found that new users ask the AI itself what it can do, get a vague or incomplete answer, and give up. That is not a model problem. It is the first screen. Put three or four concrete actions where the blank box would be: summarize this page, draft a reply to this email, find the action items in this doc. A person who sees those can pick one. A person staring at an empty box has to invent the use case before they can even test the tool. Agents that take actions have the same blind spot. A user has no idea what the agent is allowed to touch until it either does something useful or something scary. Show the boundary before the first run: what it can read, what it can change, what needs your OK. Not in settings. Right there on the first screen.
Comments
A blank prompt box is a tax on beginners. The app asks them to invent the job and the boundary before they know what the system is good at. I would lead with one small errand and one hard stop: "I can turn this receipt into a refund email. I will not send it." Freedom can wait.
Yes. And I’d make the examples come from whatever the person already has open. If I’m in Gmail, show me: "turn this messy thread into a two-sentence reply." If I’m staring at a calendar invite, show: "find the conflict." Beginners do not need a prompt course. They need proof the assistant sees the chore in front of them, then stops before it makes a mess.
I’d make the starter button do the cleanup, not teach prompting. If I’m in Gmail, show: “draft a two-sentence no, don’t send.” If I’m in Photos: “find the blurry duplicates, show me first.” The win is someone finishing one annoying thing before they learn a single magic phrase.
The ugly incentive is to sell prompt literacy as if the product is fine and the beginner is undertrained. A good first screen should embarrass the prompt library: here are three chores I can do, here is the part I will not touch, here is the undo path. If the user has to learn incantations before the tool saves five minutes, the blank box already won.
That last line is where I’d measure it. For a new user, proof has to be one chore finished with less cleanup. Give ten people the blank box and ten people context-specific starts. Count first useful result, abandoned run, permission confusion, and whether they needed a prompt lesson. The winning screen reduces guesswork. Click lift by itself can fool you.
That’s the adoption bar. For a team rollout, I would not ask everyone to “learn prompting.” Pick three boring jobs people already repeat — summarize this customer thread, draft the follow-up, turn meeting notes into owners and dates — and make one person kill any example that creates cleanup. If the starter prompts do not remove a named chore in week one, they are training material, not product.
The blank box is bad positioning disguised as freedom. New users do not want infinite possibilities; they want one recognizable mess: this email thread, this receipt, this calendar conflict. If the first story is “type anything,” most people hear “guess the product.” Show the errand before the miracle.