Skip to content
← All selected work

Absol X / Case study

From a conversation to an order.

Can an AI conversation carry a customer all the way to the next real action?

Contribution
Machine Learning Engineer
Period
Feb 2025 — Mar 2025
Location
Kandy, Sri Lanka
4 stages

Connected sales workflow

4

Sales steps automated

1

ERP running the operation

Reported in the supplied CV. See the evidence note below for scope and measurement limitations.

01 / The situation

A car dealership needed an AI sales agent for onboarding, negotiation, test-drive appointments and order placement, alongside an ERP for its operations.

The project connected an AI sales agent for a car dealership with the operational system supporting customer interactions.

What made it an integration problem

The stated scope included customer onboarding, price negotiation, test-drive appointments and order placement. An ERP supported business operations and customer data.

02 / My contribution

The parts I built.

  1. 01

    Designed and built a full-fledged AI-powered sales agent handling onboarding, price negotiation, test-drive appointments and order placement.

  2. 02

    Developed a robust ERP system to streamline operations and manage customer interactions.

  3. 03

    Used ML techniques to improve agent efficiency and automate the sales workflow end-to-end.

Conversational AIERPAutomation

03 / The system

Follow the information.

  1. 01Customer onboarding
  2. 02Price negotiation
  3. 03Test-drive appointment
  4. 04Order placement
  5. 05ERP / customer operations

Conceptual workflow reconstructed from the CV. This is not a screenshot of a client system.

04 / An engineering reading

Why the connections matter.

The agent and ERP were both part of the delivery. This connects conversational capability with the systems that hold customer information and support subsequent actions.

The tradeoff to pay attention to

Negotiation and order placement require clear authority boundaries. The supplied CV does not describe approval policies or integration failure handling, so this case study does not claim those controls were implemented.

This section interprets the delivered scope. It does not claim an undocumented decision process.

05 / What supports this story

Keep the claims close to the evidence.

The CV confirms the sales agent, its four workflow stages and the ERP. It does not establish 24/7 availability, conversion uplift or staffing savings; none are claimed here.

Read the source CV ↓

Another problem, another system

Teaching machines to see

Discuss a similar problem ↗