Makani Tech: Build. Automate. Evolve.

Case studies · Cloud kitchen, 3 brands

Cloud kitchen: one morning report instead of three dashboards

About 93 manager hours a month back from reports, review replies and purchase lists

Hyderabad, Telangana, India · Tier 1 city25 people
saved a month
93 h
saved a month
manager time a month
₹32,550
manager time a month
sales summary on WhatsApp
8 am
sales summary on WhatsApp
to build
2–3 weeks
to build

About this case study: it is based on a business typical of the ones we work with, not a named client, and every number comes from the assumptions at the end of the page. Swap in your own and the sums still work.

The problem

Every morning starts with downloading reports from two partner dashboards for three brands and merging them into one sheet. Review replies wait until the evening, and low ratings sit unanswered.

Stock is counted on paper, and the purchase list for vendors is put together from messages sent by the kitchen team.

What we build

  1. 1

    Sales in one place

    Daily reports from the partner platforms are collected into one sheet, and a short summary by brand reaches the owner on WhatsApp at 8 am.

  2. 2

    Review replies drafted

    An AI step drafts a reply to each review in the brand's voice. The manager approves or edits in a tap.

  3. 3

    Low stock alerts

    The kitchen updates a simple stock sheet at closing. Items below their level go into a draft purchase order.

  4. 4

    Vendor orders

    After approval, the purchase list goes to each vendor on WhatsApp.

Before and after

StepBeforeAfter
Daily sales reportAbout 1.5 hoursAutomatic
Replying to one reviewAbout 2 minutesAbout 20 seconds to approve
Purchase listAbout 30 minutesDraft ready to approve

Where a person stays in control

No review reply or vendor order goes out without the manager's approval. What can be pulled from each delivery platform depends on the reports it offers; we check that first.

Running cost

Roughly ₹3,000–6,000 a month for AI usage, messages and hosting.

Tools

  • Swiggy and Zomato partner reports
  • Google Sheets
  • WhatsApp Business API
  • AI model
  • n8n

How the numbers work

  • Daily MIS: 1.5 hours × 30 days = 45 hours.
  • 40 reviews a day at 2 minutes is about 40 hours a month; approving drafts at 20 seconds saves about 33 hours.
  • Purchase list: 30 minutes × 30 days = 15 hours.
  • Manager time costed at ₹350 an hour: 93 × ₹350 = ₹32,550.

Estimates, not promises. Use the savings calculator with your own hours and costs.

Want this for your business?

A free 30-minute call is enough to tell whether it fits, what it would take and what it would cost.

More case studies

Restaurant group, 4 outletsPune, Maharashtra, India · Tier 1 city

Restaurant group: table bookings, reminders and feedback that reaches the manager

About 75 manager hours a month back, and unhappy guests heard the same day

Weekend tables are booked by phone and Instagram DMs, no-shows leave tables empty, and feedback is a paper card nobody reads.

saved a month
75 h
saved a month
manager time a month
₹26,250
manager time a month
reply to a low rating
Same day
reply to a low rating
to build
2–3 weeks
to build
Read the case study
Textile wholesaleSurat, Gujarat, India · Tier 2 city

Textile wholesaler: WhatsApp orders that type themselves

About 178 hours a month of order typing and dispatch calls taken off the desk

Dealers send orders as WhatsApp messages, photos of handwritten lists and voice notes. Three people retype them into a sheet and then into Tally, and spend the afternoon answering "has my parcel left?"

saved a month
178 h
saved a month
staff time a month
₹62,300
staff time a month
to check an order, down from 12
2 min
to check an order, down from 12
to build
3–4 weeks
to build
Read the case study
All case studies