Why Is My AI Agent Asking Me Questions After I Press Enter?
You pressed the up arrow and the screen changed. The questions are part of the build. How I answer them, and what makes an AI agent ask.
It's normal. After you press the up arrow, the screen changes and the AI agent asks for input with multiple choice questions. Pick an option, or choose the one that says other and type your own answer, then submit.
You dictated your goals, pressed the up arrow, and the page you were looking at turned into something else. Then questions showed up that you didn't ask for. I told the group on October 7, 2026 to expect this before anyone pressed anything.
Is it normal for the screen to change after I press the up arrow?
Yes. I said so twice, in two different ways:
From the recording, 16:51. So what's going to happen next is our screen is going to change slightly. Do not be alarmed.
From the recording, 17:00. So the chat feature is there for us to get started in a really simple way, but we'll now see more controls once we hit the up arrow.
I also said it's part of the normal process (17:09). What you'll see after that is the AI agent thinking. It writes out what it's doing as it goes, based on the instructions you gave it (17:12).
What do I do with the questions?
The steps, as shown October 7, 2026:
- 01
Read each question. The AI agent gives you multiple choice options.
- 02
Click the option that fits.
- 03
If none fits, choose the option that says other (option D on my screen) and type your answer.
- 04
Press submit.
- 05
The AI agent begins to think again.
You should see the AI agent begin to think again. At 17:26 I described the screen at the moment it asked me:
From the recording, 17:26. If you're following along on my screen, my agent is now asking for input. It's provided multiple choice questions for me.
From the recording, 17:35. I can select from those options, but if none of those fit, I can use option D, which is other, and I can type in my response.
From the recording, 17:46. So if you have questions on your screen, I'd like you to go ahead and answer those questions and hit submit.
In my setup video I described the same screen as a set of choices plus a space to type what I want, for when none of the choices is right. The recording shows option D as other.
What makes an AI agent ask questions?
Two things I showed, and one setting.
You left something open. At 13:05 I pointed out that I hadn't told my AI agent how to give me the information outside of a dashboard, so it would ask me:
From the recording, 13:12. So it'll ask me clarifying questions in a moment.
You asked it to. When I built the skills, I typed that I wanted two of them and asked for three or four questions to customize them (37:10). At 38:33 I told the group what to expect:
From the recording, 38:33. What you'll see next is that your agent will begin to think and it should come back and ask you a few questions.
An ability is on. Gumloop's documentation lists Ask Question as an ability that's on by default, and says it lets the AI agent pause and ask you a structured, multiple choice question when it needs a decision. You can switch it from the Abilities section of the tab named Agent. Checked on 2026-11-05 against Gumloop's Agents documentation. In part two of my setup video I said to keep it on, and why: it lets the AI agent clarify with you, so it isn't burning or wasting tokens.
On my relationship to Gumloop, I said this:
From the recording, 33:22. I don't work for Gumloop. I found this tool over the summer through Lenny's podcast, and I started using it and have since made myself an ambassador for them. I've created a relationship with Gumloop. I am not an employee.
More on that answer: Do you work for Gumloop? (the answer from the session).
What goes wrong
Pressing the up arrow too early. Before the dictation step I told the group to hold off:
From the recording, 13:46. Do not press the up arrow yet. Only speak into your agent.
Taking the screen change for an error. I said the new controls are part of the normal process and not to be alarmed.
Choices that don't match what you meant. That's what the other option is for: type your own answer.
What the recording doesn't show: how many choices each question had on every screen. I read out option D at 17:42, and my setup video describes it differently, so I'm not giving you a count.
Where this comes from
This article grows from the session I taught live with Women Applying AI on October 7, 2026. The quoted passages are my own words, taken verbatim from the recording. The steps, tables and checklists around them were drafted by my team's AI agents from those words and my published pages, and checked against the recording before publishing. The lines about the ask-questions ability come from part two of my published setup video on YouTube and are restated, not quoted. Platform facts that have a public source carry the dated line above, and screens change.
Build Your First AI Agent in One Hour: the full session with the clips, the prompts and the transcript.
Related reading: How Do You Dictate Goals to an AI Agent?, What Does Run a Test Mean for an AI Agent?, Which Abilities Should I Turn On for My AI Agent?.
Frequently asked questions
Is it normal for the AI agent to ask me questions after I press the up arrow?
Yes. On October 7, 2026 I told the group the screen would change slightly and not to be alarmed (16:51).
What do I do if none of the choices fit?
Choose the option I called other, type your answer and submit (17:35).
Can I tell the AI agent how many questions to ask?
I did when I built skills: I asked for three or four questions (37:10), and at 38:33 I told the group to expect a few back.
Where do I turn the questions off?
I keep the ability on, and in part two of my setup video I said why. Gumloop's documentation puts the toggle in the Abilities section of the tab named Agent.
Build something that actually runs your workflow.
A focused, free 60-minute live session with Jacqueline. You build alongside her, on your own real task, and leave with an AI agent that is already running.