ProjectsJanuary 6, 2026

LeadBot AI: WhatsApp Automation for Lead Qualification

Overview

Artesa's commercial team was generating inbound leads through paid campaigns, but the pipeline had outgrown the team's capacity to handle it manually. Response times were slow, salespeople were starting conversations without context about the prospect's needs or intent, and with no customer service department, every general inquiry landed on the same people responsible for closing deals. The mandate: build a system that qualifies B2B leads, handles B2C inquiries, and delivers only sales-ready opportunities to the team. Result: 85% of conversations handled autonomously, 24/7, with zero additional headcount.

The Build

Integration Architecture

Bitrix24 has no native WhatsApp connectivity, so I built the integration stack from scratch. The solution used BotSL IA, a Bitrix24 Marketplace application, to create the chatbot layer and connect open communication channels, with the WhatsApp Business number linked directly to Artesa's Meta account for compliance and operational control.

AI Model Selection

The chatbot runs on GPT-4o mini, chosen deliberately. High conversational accuracy, strong performance in customer service contexts, and cost efficiency at scale. Keeping operational costs low without sacrificing response quality was a real constraint, not an afterthought. Temperature was set to 0.10. In sales and customer service automation, precision matters more than creativity. A chatbot that improvises in a qualification flow is a liability.

Knowledge Architecture

Rather than a rigid decision-tree, the system uses natural language understanding, which means it handles unpredictable user inputs without breaking. To maintain accuracy and prevent hallucinations, I built a structured knowledge base from three custom documents:

Artesa Communication Guidelines: tone of voice and brand rules
B2B Sales Manual: qualification logic, information boundaries, and conversation flow
B2C Sales Manual: product FAQs, service scope, and escalation criteria

Each document was developed and refined using Gemini Pro to ensure consistency across complex instruction sets. System instructions were configured through OpenAI's Assistant Playground, covering role definition, language rules, and the data extraction logic required to qualify leads with context (product interest, volume, and location) before a human ever enters the conversation.

Results

LeadBot AI became a permanent operational system, not a pilot. It reduced friction in the commercial process, delivered B2B leads to the sales team with full qualification context, established B2C customer service coverage the business didn't previously have, and compressed response times from hours to seconds. 85% of conversations handled autonomously. The team's attention went where it should have been the whole time: closing.

What This Demonstrates

Every decision in this project, including tool selection, model choice, temperature configuration, and knowledge base design, traces back to one question: what does the team need to stop doing manually, and what does the system need to do reliably in its place? That's the only lens that matters when building automation for real commercial operations. Stack:

WhatsApp Business APIBitrix24 CRMBotSL IAGPT-4o miniOpenAI Assistant PlaygroundGemini ProMeta Business Suite

Related projects

Quick Metal Shop & Dakoma Roofing: AI-Powered Ad Creatives

3.92xROAS

How a lean, one-person production pipeline, built entirely on AI avatars, cloned voices, and rapid editing, replaced traditional video shoots and drove measurable results across two brands, two industries, and two ad objectives.

Read case study

Quick Metal Shop: The Brand Comes to Life

How a brand manual built from the ground up became one of the standout booths at ArquiExpo 2026, and a corporate video carried by a fully original soundtrack, composed with AI.

Read case study

Quick Metal Shop: ArquiExpo 2026 Interactive Gallery Application

48hdev to deploy

Custom-built, vertically-oriented interactive touchscreen web application showcasing 285 architectural panel variants, designed, developed, and deployed in 48 hours for ArquiExpo 2026.

Read case study

Quick Metal Shop: Building a Marketing Department From the Ground Up

Establishing a complete full-stack marketing department and digital infrastructure from scratch, including brand manual, CRM automation, paid media, and AI content engines.

Read case study

Dakoma Roofing: Freelance Rebranding & Digital Automation

Complete brand overhaul, digital channel modernization, AI-powered SEO automation, and premium ad creative production for a B2C roofing and construction services provider.

Read case study

ATV Riders: WhatsApp Lead Automation with Kommo CRM

200+leads/day

End-to-end WhatsApp automation system built for a high-volume ATV dealership, filtering 200+ daily Meta leads through an intelligent chatbot, routing only sales-ready prospects to the commercial team.

Read case study

Building This Portfolio: AI-Assisted Development in Practice

<2mindeploy time

How I designed, built, and deployed a production-grade Next.js portfolio using AI agents as my development team, and what that says about the future of technical work.

Read case study