Client onboarding

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. 1Describe your business and this project in your own words, assume we know nothing.

   Voice · 120s

   AI extracts: business: string, project_summary: string, target_customer: string

2. 2Ninety days from now, what does a home-run outcome look like? Be specific.

   Voice · 90s

   AI extracts: success_metrics: string[], measurable: boolean

3. 3What has gone wrong with vendors or agencies before, and what should we never do?

   Voice · 90s

   AI extracts: past_failures: string[], red_lines: string[]

4. 4Who gives final approval on deliverables?

   Choice

   Me, directly / Me plus one partner / A committee or board / Not decided yet

   AI extracts: approval structure; single decision-maker yes/no

5. 5Paste links and access notes: site, brand assets, analytics, anything we will need.

   Text

   AI extracts: urls: string[], access_gaps: string[]

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.

Score for engagement risk, low score = high risk. High: articulates measurable 90-day outcomes, names a single clear decision-maker, and states expectations and red lines openly. Medium: enthusiastic but success is described in feelings rather than metrics, or approval runs through a committee. Low: cannot describe what success looks like, contradictory expectations, a history of blaming every previous vendor, or scope described as "everything". Flag mismatches between the stated goal and the stated approval structure.

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-onboarding →