Build an AI Demo Request Form That Qualifies Leads

Every demo request deserves a fast answer, but not every request needs the same one. In this free lesson you build a "Book a demo" form for Northwind Scheduling Software in Lovable and connect it to an n8n AI agent that rates each lead hot, warm or nurture, saves it to Google Sheets and emails the prospect one next step that fits.

What you will build: a demo request form with AI lead qualification

The form asks four things: name, email, what the prospect needs help with, and team size. You build it in Lovable by pasting one prompt, with no coding. When someone submits it, the data goes to an n8n webhook. An AI Agent reads the request, rates the lead, adds a row to a Google Sheet called Leads, and sends a short reply through Gmail. A Respond to Webhook node tells the form it worked, and the prospect sees a confirmation.

In the test, Dana Whitfield writes that her company schedules 12 cleaners on a spreadsheet that keeps breaking and wants to switch this month. The agent rates that hot, saves the row, and emails two demo times this week.

How the agent rates each lead

The system message gives the agent three simple ratings. Hot means 5 or more staff and a plan to switch within a month. Warm means a clear need but no timeline. Nurture means they are just looking. Each rating comes with its own next step: hot leads get two demo times this week, warm leads get a link to book a demo, and nurture leads get a helpful guide with no pressure. The Leads sheet keeps the four form fields, so the team can see exactly what each prospect wrote.

Who this is for

This lesson is for sales and marketing teams at small B2B companies, founders who still answer every demo request themselves, and SDRs who want inbound leads sorted before they pick up the phone. You do not need to code. You need your own Lovable, n8n, OpenAI and Google accounts to build it for real.

Step by step: what you do in the lesson

• Build the form: start a Lovable project, paste the prompt for a Book a Demo form and build the app.
• Webhook trigger: start an n8n workflow on a webhook call and set it to answer through a Respond node.
• AI Agent: define the prompt manually with a template that pulls name, email, need and team size from the webhook, then paste the system message.
• Chat model: add OpenAI, save your API key as a credential and pick gpt-5-mini.
• Create the spreadsheet: name it Leads and type the headers Name, Email, Need and Team Size.
• Sheets tool: sign in with Google, pick the Leads spreadsheet and Sheet1, and map each column.
• Gmail tool: add Gmail and connect your Google account so the agent can reply.
• Respond node and publish: add Respond to Webhook and publish the workflow.
• Add the secret: copy the production webhook URL and save it in Lovable as N8N_WEBHOOK_URL.
• Test the form: fill it with sample data, click Book a Demo and check the new row in the spreadsheet.

Why it works

Speed matters with inbound leads, and so does fit. The form collects just enough to judge fit, and the system message turns your qualification rules into plain sentences the agent follows every time. The webhook URL lives in a Lovable secret instead of the page code, which is safer and easy to change. Every request lands in one sheet, so nothing sits in an inbox waiting for someone to notice it.

Common mistakes this avoids

• Slow replies. The prospect gets an email within moments of submitting, not whenever someone checks the inbox.
• One reply for everyone. A 12-person team ready to switch and a student doing research no longer get the same canned message.
• Lost leads. Every request becomes a row in the Leads sheet, even on weekends.
• Pushy follow-up on cold leads. Nurture leads get a helpful guide instead of a hard sell.

How to use this on your sales team

Swap in your own product, your own definition of a hot lead and your own next steps. If your team qualifies on budget or current tool, rename the form fields and update the rating rules to match. Put the form on your pricing page or in an ad, and let reps start the day with a sheet of rated leads instead of a pile of unread emails. Read the replies the agent sends for the first few days and tighten the rules until they sound like your team.

Frequently asked questions

How does the interactive lesson work?

Each step is shown to you first on the left (Watch). Then you do it yourself in a practice copy on the right (Your turn), and every click is checked. If you get stuck, press Do it for me. It is a practice copy, so no real accounts are touched.

Is this free?

Stepthrough is completely free. To build it for real you need your own Lovable, n8n, OpenAI and Google accounts, and some of those cost money to use. The practice copy in the lesson touches none of them.

Does the rating get saved in the spreadsheet?

In this lesson the Leads sheet stores the four form fields, and the rating decides which next step the reply email offers. You could add a fifth column for the rating in your own build.

Do I need to know how to code?

No. Lovable builds the form from a written prompt, and the n8n workflow is built by clicking and pasting.

Can I change what counts as a hot lead?

Yes. The rules are plain sentences in the system message. Edit them to match your own team size, timeline or budget criteria.

Why is the webhook URL stored as a secret?

Keeping it in a Lovable secret means it is not hard-coded in the page, and you can change it later without rebuilding the form.

More in AI Automation for Sales