Business software and compliance Case study
Mammoth Self Storage: AI storage calculator and chatbot
A chatbot for Mammoth Self Storage that estimates how much storage a customer needs from a photo or video, lists the items and their volume, finds the nearest site, quotes available units and hands off to booking.
- Client
- Mammoth Self Storage
- Service
- AI, Web apps, Integrations
- Years
- 2025–2026
- Stack
- Gemini API, Google Maps API, Firestore, Tailwind CSS and 1 more
- Platforms
- Web
Overview
Mammoth Self Storage, an Australian self-storage operator, wanted customers to work out how much space they need and reserve it in one conversation. The chatbot asks for a list of items or a photo or video of them, shows the items it found with their volumes and a total, and asks the customer to confirm or add more. It then finds the nearest site, quotes the units that are available and sends the customer to a pre-filled booking page. We built the chatbot, the integrations and the admin tools.
The challenge
Customers rarely know how much space they need, unit availability and pricing live in the operator's storage management system, and the nearest site may not have the right size free.
What we built
- A chatbot interface and a Gemini API back end that estimates item volume from uploaded images and video, with large-file support
- A conversation that lists the items found with their volumes and a total, and asks the customer to confirm or add more items
- Integration with the storage management system for unit availability, discounts, quotes and reservations
- Geolocation to find the nearest location, with lead-time rules and alternative unit sizes when the first choice is not free
- An admin interface for managing the chatbot's prompts and questions
- SMS and email notifications for customers and staff
- Pre-filled booking links so the customer lands on the right unit
- Testing and fixes across the chat flow, uploads and integrations
Technology used
| Layer | Choice | Purpose |
|---|---|---|
| AI | Gemini API | item volume from images and video, chatbot answers |
| Location | Google Maps API | nearest site |
| Front end | Tailwind CSS | chatbot and sign-up plugin |
| Data | Firestore | chat and lead data |
| Integration | Storage management system API, SMS and email | units, quotes, reservations and notifications |
What happened next
- Delivered
The work described above was delivered to the client.
- Operational facts
- Our work on this project spanned 2025–2026.
Screens
Could this be your project?
- You have a defined job in a real process that automation or AI could take on. AI services
- You need a web application with user accounts, admin tools and reporting. Website and web app development
- You work in business software and compliance and want a team that has built for it before. Business software and compliance work
Questions about this project
How long did this project take?
Our work on it ran from 2025 to 2026, with 400+ engineering hours logged in total.
What technology was used?
Gemini API, Google Maps API, Firestore, Tailwind CSS, SMS and email.
Similar work
Also Google Cloud, same industry
QCare: compliance platform for DEKRA
QCare, DEKRA's quality, compliance and risk evaluation platform on the Collabtic service platform: certification and compliance tracking, organisations, training, shop certification and headquarters dashboards, on an Angular front end and a PHP API.
Same industry, also an AI project
Ads Intelligence: AI Google Ads fleet platform
An internal web app and Google Ads pipeline for a digital marketing agency: one view of every managed account's spend, click-through and conversion figures, with an AI diagnosis that compares each account with its peers.
Also Google Cloud, same industry
MyAddressPin: unique map ID for any location
A digital address service: users create a unique 8-digit MapID for any location, share it and get route guidance, on a Node.js web app and Flutter mobile apps sharing one Firebase back end.