Quoteline: Conversational Sales for Small Businesses
Buyers ask on WhatsApp, Telegram or email and get an accurate, priced quotation in minutes, while a person takes over whenever money, complaints or fraud are involved.
A sales assistant for small businesses that sell through chat: a caterer, a corporate gift shop and an aircon servicing company in the demo. It answers questions, sends the menu with allergens, checks the calendar for capacity, collects delivery and venue details, and issues a formal quotation priced by the business's own engine. Each business switches on autopilot one message type at a time, after its staff have approved enough drafts unchanged.
Small businesses lose orders when chat enquiries wait for a reply, and lose margin when someone quotes from memory. Automating replies risks wrong prices, promises the kitchen cannot keep, and payment-detail fraud in a channel buyers trust.
Every price comes from a pure pricing engine checked against 64 hand-computed fixtures. A guard checks each reply before it is sent, and a classifier hands complaints, requests for a person and suspected business email compromise to staff. A quotation holds a slot on the calendar until it is accepted or lapses. Every business's data is isolated by tenant.
The system runs for three demo businesses with live WhatsApp, Telegram and email turns. All 12 evaluation scenarios and all 35 isolation checks pass, and a typical turn costs about two US cents. A caterer's feedback added menus with allergens, capacity per time block, venue access questions and promotions.
- Status
- Working system
- Client
- Confidential
Built to the Governed Cognitive Layer: the model reads and drafts, deterministic checks decide what it may do, and a named person approves anything that commits the business.
Let the AI hold the conversation and let your price list do the arithmetic. Start in copilot, where staff approve every reply, and switch on autopilot only for the message types your team already sends unchanged. Hand anything about payment details, complaints or a person to staff at once.
Concept paper, C-suite deck, sales pitch and live demo
The concept paper, the decks and the working portal sit behind a password. I walk owners through it live.
●Live demo (on request) →The same design rules behind this build, applied to your business in half a day.
Book the WorkshopDiscuss a build like thisScreens from the system
Demo data throughout. Customer names, accounts and payees are fictional.
Other projects
Agentic AIProject Forecourt PWP: Agentic Offers at the Fuel Pump
While a driver fuels, the pump screen offers one store item at a purchase-with-purchase price, and the fuel transaction is left exactly as it is.
See how it works →
Enterprise AIKELIX Enterprise AI Platform
Proprietary private cloud AI engine built for 6,000+ engineers on multi-billion dollar projects.
Read case study →
Enterprise AIMeinhardt AI Centre of Excellence
RAG platform deployed across 6,000+ engineers.
Read case study →
A caterer changed the price of a cake, and the assistant kept quoting the old price. The new price was live. The assistant was repeating the figure from a quotation it had already issued that morning. I changed it so that open quotations are re-priced when the price list changes, and the assistant may not mention any amount until the engine has priced it again. Most AI pricing errors I see are stale numbers, not wrong arithmetic.
