One-question intake

The questions

Each question carries an extraction hint: plain language telling the AI what to pull out of the answer. That's how a spoken ramble becomes a structured row in your inbox.

1. 1In one take: what do you do, what do you want help with, and why are you looking now?

   Voice · 90s

   AI extracts: what_they_do: string, need: string, urgency_driver: string, timeline: string|null

What the AI scores for

This rubric ships with the template and feeds the 1 to 100 score on every submission. It's yours to edit, and the AI writes its reasoning out next to each score.

One answer carries the whole signal, so score for substance per sentence. High: says what they actually do in concrete terms, names a specific need, and gives a real reason the timing is now (a launch, a deadline, a thing that just broke). Medium: clear on what they do but the need or the timing stays abstract ("growing", "exploring options"). Low: talks about ambition without a business, cannot name what they want, or rambles without answering any of the three parts. Reward brevity that covers all three; never reward length on its own.

Try it live

This is a real, working copy of the template. Answer it by voice if you like: submissions here are demo data, processed and then discarded.

Prefer a full tab? Open /f/tmpl-one-question →