Overview
Multi-aggregator order routing and inventory automation: normalises Deliveroo, Talabat, and Careem Now webhooks, auto-assigns prep stations by brand SLA, and triggers low-stock WhatsApp alerts. Order-error rate falls from 9.4% to 0.8%; kitchen throughput rises 31%.
The challenge
Running six virtual brands from one kitchen meant the head chef was manually triaging orders arriving simultaneously on three tablets, each using different order-number formats and SLA clocks. During peak hours (12–2 PM and 7–10 PM) this caused a 9.4% wrong-brand or wrong-item error rate and triggered over 40 customer refund requests per week. Inventory tracking was done by paper tally, resulting in mid-service stockouts twice a week.
The solution
Lirevon built a unified webhook normaliser that maps all three aggregator payloads into a canonical order schema with brand-specific prep SLAs. A Redis-backed station-assignment engine distributes orders to the correct prep station in under 200 ms. A perpetual inventory engine deducts ingredients against a recipe matrix on each order; when any ingredient falls below par, a WhatsApp alert fires to the purchasing manager with a one-tap reorder link.
Outcomes
Order-error rate dropped from 9.4% to 0.8%, eliminating over 37 refund requests per week
Kitchen throughput increased 31% through optimised station assignment during peak hours
Mid-service stockout incidents fell from 2 per week to zero in the first month post-launch
Aggregator tablet monitoring time for kitchen staff eliminated entirely — all orders flow to one display
Key metrics
Tech stack
Services
Client testimonial
“My chefs used to spend the first 20 minutes of a rush just figuring out which tablet showed which brand. Now everything is on one screen and the errors are almost gone.”
— محمد الظاهري، المالك والشيف التنفيذي
Related work
Last-mile delivery operator (80 drivers) · Kuwait City
Automated route-optimisation and proof-of-delivery pipeline: aggregates Talabat and Salla orders, generates optimised multi-stop manifests, and sends Arabic SMS delivery notifications with live tracking links. Failed-delivery rate drops from 14% to 3.1%; driver idle time falls 28%.
Result:Failed deliveries 14% → 3.1%; driver idle time −28%
Multi-specialty polyclinic (9 departments) · Doha
End-to-end insurance prior-authorisation automation: extracts treatment codes from doctor notes, submits PHCS-formatted PA requests to 14 insurers via API, and tracks approvals in a real-time dashboard. PA turnaround 5 days → 4 hours; rejection rate drops from 22% to 6%.
Result:PA turnaround 5 days → 4h; rejection rate 22% → 6%
Residential property manager (1,100 units) · Abu Dhabi
Automated tenant-communications and maintenance-request pipeline: WhatsApp bot triages requests, generates work orders, routes to contractors, and tracks SLA compliance. Manual PM hours per unit fall from 2.1 h/mo to 0.4 h/mo; tenant NPS rises 29 points.
Result:PM hours 2.1 h → 0.4 h/unit/mo; tenant NPS +29 pts
Book a free 30-minute audit, or message us on WhatsApp. We'll send a fixed-price proposal in two days.