Skip to content
luvish.

Case study · small-business agent

Kelly

A locally running voice and quotation agent for Indian small businesses. Kelly turns a business catalogue into practical pricing, GST, quotation and customer-support workflows across voice, spreadsheets, web, terminal and Telegram.

Codex-basedlocaldemo-readyHindi + Hinglish speechView code ↗Try boutique demo ↗

the person and the problem.

Kelly started with my cousin's shop. The work was familiar: find the right item in a catalogue, confirm its price, apply GST, prepare a quotation and answer the next customer question without losing the thread.

the person

An owner working between interruptions.

Customer questions arrive while the owner is already handling products, prices and documents. The useful tool has to fit that working day.

the problem

The answer lives across catalogues and calculations.

A quotation is not one prompt. It needs the right product record, price, GST treatment, a usable document and a final human check.

the product decision.

I did not build Kelly as a generic chatbot or as software only for electrical shops. I built a configurable agent around the business's own catalogue and the jobs people already do: quotation, catalogue lookup and customer support.

The decision: keep the agent local, use Codex for reasoning, let people speak naturally in Hindi or Hinglish, preserve Hindi in the transcript, and stop for owner review before action.

Kelly request and quotation workflowPDF, XLSX and CSV catalogues are published. Voice, web, terminal and Telegram requests use catalogue and isolated conversation retrieval to prepare prices, GST and quotations for owner review.
One grounded path. Business data comes from the published catalogue. Conversation retrieval stays isolated to that Q&A. The owner reviews the result before anything happens.

how it works.

01

import the catalogue

Bring product data in from PDF, XLSX or CSV and publish it for retrieval.

02

ask naturally

Use Hindi or Hinglish speech, web, terminal or Telegram. Hindi is kept in its native script in the transcript.

03

build the answer

Retrieve the product, work through pricing and GST, then prepare the quotation or support response.

04

review before action

Show the result to the owner. The human decides what is ready to use.

what I owned.

  • Product framingStarted from my cousin's shop workflow, then designed Kelly for quotation, catalogue and customer-support jobs.
  • Catalogue pipelineImported PDF, XLSX and CSV data, then grounded retrieval in the published catalogue.
  • Quotation workflowConnected product retrieval with pricing, GST, document preparation and spreadsheet work.
  • Conversation designAdded Hindi and Hinglish speech, native-script transcripts and isolated Q&A retrieval.
  • Working surfacesMade the core workflow available through terminal, web and Telegram.
  • Human controlKept owner review as the decision point before action.

current stage and next improvement.

current stage

Demo-ready.

Kelly runs locally today with catalogue imports and retrieval, pricing and GST, quotations, spreadsheet workflows, voice and text surfaces, and owner review.

next improvement

Make setup easier for each business.

The next step is a clearer configuration flow for catalogue fields, GST rules, quotation preferences and support behaviour, so a new business can adapt Kelly without changing its core workflow.