Weighs banquet leftovers by dish and guest count to set next event's quantities
TL;DR Ladlecount is a camera and scale station for hotel and caterer banquet kitchens. After each event every leftover pan gets weighed and recognised by dish, then matched to the guest count. Over a season it tells the chef how much of each dish to cook per hundred guests, and banquet operators pay monthly for it.
Indian kitchens overcook on purpose. In a survey of 63 Mumbai restaurants, three in four said they deliberately prepare 10–20% more than needed, and some go up to 30%[1]. Buffets waste more than plated service, and weddings and social events lose 10–15% of their food. One estimate puts wedding waste in Bengaluru alone at 943 tonnes a year[1].
Banquet chefs have good reason to be cautious, since running out of a main dish in front of 800 guests costs you the next booking. But they plan from rules of thumb and nobody records which dishes came back full. Without that record the safety margin never shrinks.
What it does, in regulatory terms: kitchen operations measurement only. It handles no food sold to the public, so the kitchen's existing FSSAI licence covers it.
After each event, staff slide leftover pans onto a scale under a camera. The camera recognises the dish from the event's menu and the scale records the weight. The system links that to the confirmed and actual guest count from the banquet booking. After a few dozen events the chef gets a per-cover quantity for each dish type, by event size and type, because a 300-guest corporate lunch eats very differently from a 900-guest sangeet.
Ladlecount doesn't measure guests' plate waste, as tray-return tools already do that for canteens. It sticks to what never left the kitchen. Food that's still safe to serve gets logged as it goes to a food-recovery group, so the hotel has a record for its sustainability report.
The user is the banquet sous-chef. The payer is the hotel's food and beverage director or the owner of a large catering firm, for whom food cost is the biggest variable line. Global tools sell on savings - one camera-over-bin vendor says clients cut food costs by 2–8% and recover their spend in 6–12 months, but it publishes no prices[2]. My working assumption is a monthly fee per kitchen, and you'll have to test it.
Hotel groups now report on sustainability, and global waste-tracking vendors already serve international hotel chains with Indian properties[2]. FSSAI rules on recovering and redistributing surplus food have been enforced since 2019[1], which gives kitchens a legal channel for good leftovers. And cheap edge cameras make a per-kitchen station affordable.
There's no public figure for banquet food waste or spend on waste tracking in India. The narrowest evidence is the 10–15% loss at weddings and social events[1]. One US waste-tracking firm reports that kitchens waste 5–15% of what they buy, and that cutting waste trims purchases by 2–6%[3].
For adjacent context only, Indian households waste about 68.7 million tonnes a year[4].
The biggest camera-over-bin vendor runs systems in more than 3,500 sites in 90 countries, mostly hotels and contract caterers, and names no Indian client on its site[2]. Another tracks kitchen and plate waste for large contract caterers[3]. Both are built around bins and à la carte or canteen service.
The gap is banquet-first forecasting that ties leftovers to Indian menus and guest counts.
| Difficulty | Moderate (40/100) |
| Starting capital | ₹60 L–1.1 Cr |
| Time to launch | 6–9 months |
Telling apart forty curries that look alike is harder than spotting a bread roll, though tying each pan to the menu helps. The real challenge is getting tired staff to weigh pans at midnight after a wedding. The forecast only gets useful after many events per kitchen, so payback takes a full season.
You don't need a new food licence, because the station runs inside a kitchen that already holds one. The hardware and data still need care.
Building this outside India? The categories above usually have a local equivalent, so check with your own regulator.
Don't let the model set quantities alone for a big event. The chef should treat the forecast as a starting point, because running out in front of 800 guests costs more than a full pan.
Want to work out the AI layer for Ladlecount? Talk to Yash →
Here's what can go south -
I like this for a founder from hotel F&B operations who can sit with banquet chefs. A pure software team will struggle, plain and simple.
First prove one thing - that one hotel cuts overproduction by a tenth across 30 events without a single dish running out.
My estimate is ₹60 L–1.1 Cr to launch, covering camera and scale stations, the recognition model and hotel pilots.
Not a new food licence, since the kitchen's FSSAI licence covers it. Wireless stations need WPC approval, and staff images fall under the DPDP Act.
Yes, anywhere large weddings and banquets overcook. Check local food safety, device and privacy rules, and whether your scale needs certification.
The free Ladlecount validation kit has the line-by-line capital breakdown, the effort scoring, the food-safety and device checklist, a 14-day validation sprint with pass/fail targets, a 90-day launch plan, 10 interview questions for chefs and F&B heads, and 5 assumptions to test. Download the kit →
Thinking about building Ladlecount or something close to it? The make-or-break work is getting tired staff to weigh every pan and chefs to trust the numbers, and I'm glad to work through that with you. If you need a hand, you know where to find me. Talk to Yash →
For illustration only. Names are fictional and ideas hypothetical; sourced facts are real but may be out of date. Nothing here is legal, financial or professional advice, and Yash Khatri is not personally liable for any use of it. Read the full disclaimer.