Lighty is a multi-agent sales assistant on Azure AI Foundry that gives Eurolux reps live product, stock and pricing and generates a professional quotation in about 18 seconds, work that used to take the better part of an hour.
Innovate with Azure AI Apps and Agents
Microsoft
Delivery partner
Practice
The results
Eurolux, one of South Africa’s leading lighting distributors, prepared customer quotations with an Excel-and-macros tool, looking up products, stock and pricing by hand across catalogues and the ERP. Matching a client’s need to the right combination of products leaned on the knowledge of a few senior reps, which created bottlenecks, slowed the sales cycle and left quotes inconsistent from one spreadsheet version to the next. A single quote took the better part of an hour.
We started with a company-grounded product chatbot and, once it had proved itself, rebuilt quoting as an agentic workflow. Lighty’s orchestrator agent, on Azure AI Foundry, reads the rep’s intent and delegates to two specialists: a stock agent pulls live product, stock and pricing from the ERP, and a knowledge agent answers from Eurolux’s own indexed lighting knowledge using retrieval-augmented generation over Azure AI Search. All three share one Azure OpenAI GPT-4o model. Lighty applies the business rules, composes the answer and generates the quotation from an approved template. The whole platform runs inside Eurolux’s own Azure tenant in South Africa North, behind Microsoft Entra ID single sign-on, with prompt guardrails and content safety at the boundary. Every answer is grounded twice over, in approved product knowledge and in live ERP data, so pricing stays correct and the model does not invent products. It is built on our reusable FirstAi framework and run like software: infrastructure as code in Bicep, CI/CD in Azure DevOps, and full telemetry and audit logging in Application Insights.
Lighty went live in mid-2026 and is now Eurolux’s primary quotation platform. A quote that took about an hour by hand now takes roughly 18 seconds, with product and price confirmed in about a second. Quotation preparation time is down 54%, giving each rep around two hours back a day, and on Eurolux’s own figures the platform saves about R633,600 a year and paid for itself in roughly eight months. New reps get productive far sooner, quotes come out consistent and accurate every time, and the product knowledge that used to live in a few people’s heads is now captured and available to everyone.
There is much excitement about the Lighty sales assistant agent. First Technology has deployed the most innovative emerging technology solution into Eurolux, something few of our other vendors were ever able to do.
Similar work in Retail & Supply Chain
Fashion Retailer
First Digital runs a major fashion retailer’s enterprise service management on Freshworks Freshservice, from Azure single sign-on to WhatsApp live chat, across roughly 1,400 agents.
Practice
Enterprise Service Management
Leading Shoe Retailer
A modular, cloud-based One App that rolled out to more than 400 stores at once, pulling stock takes, sales tracking and ticketing into a single place.
Practice
Cloud-native app development
Staffwear
A full online shopping and fulfilment experience for Staffwear, built on nopCommerce and Azure and live in three months to keep sales moving through lockdown.
Practice
Cloud-native app development
Get in touch
Send us the gist of what you are trying to do. The right person from First Digital will be in touch within a working day.
