(build 01)sample build

A sample build: how we would design lead handling for a business whose enquiries arrive across several channels and wait for whoever is available. It is an illustration of our approach, not a client project, and shows each step from the ad to the sales call.

the problem
Inbound leads were being handled manually across several channels, and response times depended on who was free.
built for
Faster responses, automated qualification, less manual work and the same follow-up for every lead.

(01)the system

how it runs, step by step.

The system for AI lead qualification and sales automation
  1. 01Meta / Google Ads
  2. 02Landing page
  3. 03AI lead qualification
  4. 04WhatsApp
  5. 05CRM
  6. 06Sales team
  1. 01

    Meta / Google Ads

    Meta lead ads and Google Search campaigns send traffic to one destination, with UTM tags and click IDs captured so every lead keeps its source.

  2. 02

    Landing page

    A focused page for each offer with a short form and a WhatsApp button, tracked in GA4 and Google Tag Manager so we can see where people drop off.

  3. 03

    AI lead qualification

    An agent built on an OpenAI or Claude model reads each enquiry, asks the questions sales would ask (budget, timing, need) and scores the lead against rules you agree with us.

  4. 04

    WhatsApp

    The agent replies through the WhatsApp Business API within minutes, books a call when the lead is ready and hands over to a person when a question needs one.

  5. 05

    CRM

    n8n writes the lead, the conversation and the score into HubSpot or Zoho CRM, assigns an owner and starts the follow-up sequence.

  6. 06

    Sales team

    Sales get a short summary of each qualified lead and a booked slot, so the first call starts from what the buyer has already said.

(02)what we would measure

how we would know it works.

Consider this build if leads come in through ads, forms and WhatsApp, and how fast they get a reply depends on who happens to be at a desk. It suits teams that want every lead asked the same questions before sales spends time on it.
  • Time to first response
  • Lead to qualified rate
  • Qualified to booked call rate
  • Cost per qualified lead

(05)questions

this build, answered.

An AI agent reads each new enquiry, asks the questions your sales team would ask, and scores the lead against rules you agree in advance. It usually runs on an OpenAI or Claude model, talks to the lead by WhatsApp or on the website, and passes anything it cannot answer to a person. Qualified leads arrive in the CRM with a score and a short summary.

An automation tool such as n8n moves it across the moment the conversation ends. The lead, the full chat, the source from the original ad and the qualification score are written into HubSpot or Zoho CRM. The workflow then assigns an owner, starts the follow-up sequence and, when the lead has booked a call, puts that slot in the right calendar.

Typically a few weeks from agreeing the questions to the agent going live. Most of that time goes into writing the qualification rules with your sales team, getting the WhatsApp Business API approved and testing the agent on real past enquiries. It is a fixed fee for the build, and a flat monthly fee if we run and improve it afterwards.

(06)your move

want this built in your tools?

Tell us where the bottleneck is. We'll show you what we would automate, build or optimise first.

growth audit · 30 min · google meet · with the founders

  1. 01

    the bottleneck

    Where time, money or customers are leaking, in your tools and numbers.

  2. 02

    the first build

    What we would automate, build or optimise first, and why that one.

  3. 03

    what it takes

    Scope, timeline and a fixed price. If we are not the right fit, we say so.