Re:Drink
Food and Beverage

Re:Drink

How Re:Drink improved refill forecasting and maintained 100% dispenser uptime with Nixtla's TimeGPT, saving 1 hour per day on manual forecasting
Re:Drink

+365 h Saved

Automation of forecasting with TimeGPT saves the team approximately 1 hour per day, or roughly 30 hours per month

100% Uptime

Accurate refill predictions ensure that dispensers remain operational throughout business hours

About Re:Drink

Overview

Re:Drink is a Munich-based startup offering a bottleless smart beverage dispenser for offices, universities, and business spaces. The countertop IoT unit dispenses filtered tap water, enriched with natural flavor concentrates, and lets users customize each drink's flavor intensity, sweetness, and carbonation. More details can be found on their website, Re:Drink — Die Flaschenlose Getränkelösung

Aligned with a strong sustainability mission, Re:Drink eliminates more than 51,000 bottles per year and cuts CO₂ emissions by 93% at client sites through its packaging‐free approach. Early deployments have seen hundreds of people using the dispenser daily, as highlighted in Re:Drink's usage data

The team's vision of decentralizing bottling plants aims to reduce beverage supply logistics by approximately 85%, providing a 24/7 refreshment station that enhances workplace experience and supports sustainability goals

Re:Drink integrates IoT hardware with cloud intelligence to enable real-time monitoring and 'flavor forecasting', predicting when flavor concentrates and CO₂ cartridges will deplete

Re:Drink overview
CHALLENGES

The Challenge

Re:Drink needed to accurately predict when its smart dispensers would require refills of flavor concentrates and CO₂ cartridges to ensure 100% uptime without overstocking

  • Manual inventory tracking is tedious and error-prone, as discussed in Why the beverage industry needs IoT?
  • There is a risk of stockouts or overstock due to inaccurate predictions
  • Initial manual models did not scale as deployments grew
OUR APPROACH

The Solution

Re:Drink implemented Nixtla's TimeGPT to replace its manual forecasting models, achieving rapid, accurate, on-demand predictions through a simple API integration

  • Leveraged TimeGPT for state-of-the-art, on-demand forecasting
  • Achieved rapid predictions without managing complex training jobs
  • Integrated seamlessly with existing IT infrastructure
  • Eliminated the need for continuous manual model updates
Alex Colucci's company logo

Implementing Nixtla's automated forecasting solution has transformed our operational efficiency. As a technical founder managing multiple business functions, I've been able to reallocate critical resources from manual prediction work to strategic initiatives that drive our core business growth and innovation

Alex Colucci
Co-founder & Tech Lead
Nixtla's TimeGPT delivered measurable ROI

Business Outcomes

Improved Uptime

  • Eliminates stockouts
  • Ensures continuous service availability

Time Savings

  • Saves 30 hours per month
  • Reduces manual monitoring workload

Scalable Forecasting

  • Automated predictions scale with the customer base
  • Supports just-in-time delivery