IC Studio
All cases
HVAC · Commercial & residential climate equipment

AI Assistant for Lead Qualification & Customer Support

How to scale sales team capacity during peak season without proportional headcount growth — an assistant integrated into the online chat and sales funnel.

Discuss your situationSee all cases
Client testimonial

Yurii · Owner · company under NDA

“Since 2019, we have developed the system with IC Studio step by step — from the online store and proposal automation to lead handling.”
Read full testimonial ↓
Industry
HVAC · Commercial & residential climate equipment
Format
Project development with ongoing evolution
Our Role
Discovery · Architecture · AI Engineering · Integrations
Platform
Online Chat + Knowledge Base + CRM
Focus
Lead Qualification · 24/7 Support · Business Actions
Case at a glance

The scale of demand and the new enquiry model

01
×10
Enquiry traffic during peak season
02
2
Experienced sales reps handling the flow
03
70%
Of the customer journey automated before sales joins
04
24/7
Answers and enquiry capture
Real scenario · identifying details removed

From “I need an AC for a three-bedroom flat” to a prepared commercial request

The customer describes a situation, not a catalog model. The assistant translates an everyday request into clear options, checks them against current products, and gathers context for the next step.

AI
AI assistantOnline · 24/7
Customer

I need an AC for a three-bedroom flat

AI assistant

There are two main approaches: one system for the shared living area, or separate units for individual rooms. A single unit will rarely provide even comfort throughout the flat.

01

Gree Pular Inverter R32 ECO GWH12AGBXB-K6DNA4K WiFi

up to 35 m² · inverter · Wi-Fi · from 24 dB

02

Gree Pular Inverter Arctic R32 GWH12AGC-K6DNA4F Silver

up to 35 m² · A++/A+ · stronger airflow

03

Gree Bora New GWH18AACXD-K3NNA2B

up to 50 m² · for a larger shared area

To recommend the right configuration, what is the total area and which rooms need cooling?

Living room onlyLiving room + 1 bedroomAll 3 rooms
Next step

Prepare two proposal options: one system or a configuration for 2–3 rooms.

What happens behind the answer

One short request starts a connected process

  1. 01

    Recognise the situation

    A ‘three-bedroom flat’ becomes a clear task without a model code or technical vocabulary.

  2. 02

    Match the constraints

    Floor area, number of rooms, and intended use are linked to suitable current models.

  3. 03

    Find the missing context

    The assistant asks a clarifying question instead of guessing the configuration.

  4. 04

    Prepare the next step

    Instead of a generic answer, the customer gets a clear choice: refine the need or move to a proposal.

Reconstructed from a real production conversation. The seller’s identity, prices, links, and other identifying details have been removed.

Operational Flow Architecture

Before automation

During peak season, every enquiry reached the same two-person team without prior qualification.

  1. 01
    Limited team capacity2 experienced sales reps
  2. 02
    Peak season amplifies demandup to ×10 enquiry traffic
  3. 03
    Every request enters the same queueno qualification before sales involvement
    PriceStockSelectionReady to buy
  4. 04
    Every request consumes sales attentioninformation and purchase intent look equally urgent
  5. 05
    The queue grows and responses slow downhigh-intent buyers wait alongside routine questions
  6. 06
    Commercial enquiries disappear into the volumepurchase-ready prospects are at risk of leaving
Accumulated effect

Commercial priority became visible only after the team had manually worked through the queue.

After automation

The assistant receives the entire flow and identifies the enquiry type before a sales rep joins.

All incoming traffic
AIQualification
Informational inquiry
Client
Assistant
Info / spec question
Instant 24/7 answerNo rep time spent
Commercial request
Client
Assistant
Buying intent detected
Sales rep receives qualified leadWith full context & transcript
The operational challenge
01

Seasonal demand exceeded team capacity by 10x

During heatwaves and peak season, inquiry volume surged almost 10-fold, far exceeding the throughput of a 2-person sales team. Speed of first response became critical.

02

Expert time was drained by repetitive questions

Managers spent hours answering routine questions about pricing, stock, Wi-Fi setup, and legacy models instead of consulting high-intent buyers.

03

Hiring didn't align with seasonal unit economics

Training a new HVAC sales rep took 5–6 months due to technical complexity (capacities, system types, refrigerants, installation limits). Premature hiring was expensive, while off-season overstaffing was inefficient.

What we build

Four capabilities work as one connected process

This is not a standalone chat layer. The assistant is connected to the catalog, sales logic, and business actions — from the first question to a prepared enquiry.

Catalog01

Current models without manual searching

Catalog guidance & alternative matching

The assistant provides prices, stock, system capacity, and technical specs. If a requested model is out of stock or archived, the system recommends a compatible active alternative.

  • Instant active catalog lookups
  • Functional comparison across models
  • Automatic alternative matching for legacy items
Qualification02

Sales joins when genuine buying intent appears

Lead qualification & rep offloading

Separates informational questions from real sales intent. Customers get instant answers to general questions; when buying intent surfaces, the lead is handed off to a manager.

  • Filtering info requests from sales opportunities
  • Sales reps spend zero time on basic lookup routine
  • Seamless lead handoff to sales reps
Business actions03

A conversation becomes an enquiry, order, or proposal

Triggering business actions inside the chat

Performs real business actions in the sales funnel, delivering qualified leads with full context and contact details straight to CRM.

  • Callback request creation
  • Order placement
  • Commercial proposal (RFQ) generation
  • Full conversation history attached to lead
Context04

The next question continues the conversation instead of restarting it

Server-side dialogue context storage

Custom server-side context state storage enables multi-turn dialogs. The system tracks conversation history and understands follow-up questions.

  • Server-side message history storage
  • Multi-turn follow-up handling ('Do you have this model in white?')
  • Reps start sales conversations with complete context
How the system became reliable
01

The system had to learn data grounding

Early prototypes answered too confidently even when information was missing. Reducing hallucination rates and building quality controls became a top priority.

10% → 1% hallucination rate within 2 months
02

The knowledge base mattered as much as the model

Product cards alone were insufficient. We transformed scattered company knowledge into one unified operational base.

Knowledge base expanded by +300% (PDFs, shipping, specs, legacy items)
03

Customers don't speak catalog language

Users ask: 'Need an AC for a 3-room flat', not 'Gree Pular Inverter GWH12AGBXB-K6DNA4A'. The retrieval engine had to be trained on natural customer phrasing.

Handling typos, transliteration, colloquial names & intent context
04

Coherent dialogue requires state memory

Standard chat platforms didn't pass history. We engineered custom server-side context storage so turns were processed as a single conversation.

Multi-turn clarification support: 'Do you have this exact model in white?'
The operational outcome

Sales conversations now begin with prepared context

The assistant handles the first layer of the conversation: answering, clarifying the need, and handing over an enquiry that is ready for a person to act on.

  1. Team focus01

    Sales time goes to commercial leads

    Routine information requests are handled before a sales rep needs to join.

  2. Qualification02

    Seasonal traffic is filtered upstream

    Commercial enquiries reach the team with the relevant context already collected.

  3. Capacity03

    More enquiries without proportional headcount growth

    The team can absorb peak demand without maintaining a permanently larger seasonal workforce.

  4. Context04

    The conversation does not restart from zero

    Sales sees the customer’s interests, questions, and alternatives already considered.

  5. Availability05

    Answers and lead capture — 24/7

    Customers can get information and submit an enquiry outside business hours.

  6. Measurement06

    Every assistant-led enquiry has a traceable source

    The AI channel sits inside the funnel, so its contribution can be measured separately.

Key Project Takeaway

The seasonal traffic problem was not solved by asking sales reps to respond faster. We changed the point at which a person joins the enquiry: after qualification, with the relevant context and a clear next step.

Client testimonial

Each season, we improve the system and the team’s processes step by step

We have worked with the IC Studio team since 2019. The relationship began with the development and ongoing support of our online store.

Since then, each season we have added improvements step by step: refining customer service workflows and the team’s internal processes around the seasonal nature of the business and a clear focus on sales growth. Over that time, we have moved from automating commercial proposal preparation to automating the way leads are handled.

Yurii— Owner · company under NDA

Gree

If your operations feel harder to manage than they should — we're happy to take a look.

We usually start by identifying one area that can be improved quickly.

Discuss your situation