Custom models and integrations that live inside the tools your team already opens every day.
Custom AI model development, from a New York team. A model on its own is a demo. What makes it useful is where it sits. PackShip's sizing model runs on the phone that was going to take the photograph anyway, so nobody has to open a second app, upload anything, or wait on a round trip to a server.
It estimates an item's dimensions from a single photograph, with no LiDAR. Typical error lands around a centimetre, which is less than the padding most people were going to stuff in the box anyway. From there a live 3D scene fits the item into candidate boxes while you watch, and UPS, FedEx, and USPS rates re-quote themselves every time the box changes.
The integration work is the unglamorous half and it is most of the job. React Native on the front, Postgres and Redis behind it so the rate lookups come back fast enough to feel instant, and a stack your team can hire for. The code is clean and documented, and it is yours to take over whenever you want it.
Workflow
How a custom model ends up in daily useHow we work
PackShip, layer by layer
On-device model:
A model running on the phone estimates an item's dimensions from a single photograph. No LiDAR needed. Typical error lands around a centimetre, which is less than the padding most people were going to stuff in anyway.
Three.js in React Native:
A live 3D scene fits your items into candidate boxes while you watch. Rotate it. Swap the box. See exactly how much empty air you were about to pay to ship across the country.
Carrier APIs on Redis:
UPS, FedEx, and USPS rates sit side by side and re-quote themselves every time the box changes. The cheapest safe option wins, usually by a wider margin than people expect.
Where it ended up:
Live on the App Store as a consumer product. A multi-step, error-prone chore became one photo and a tap.
Shaped around how you already work
You're sitting on data or a manual process, and you want a working result you can point at.
What integration means here
Software shaped around how your business already works, built to survive the next three years of it. Discovery maps the real problem before we write any code. What comes out is clean, documented code your team can take over whenever they want it, and support after launch for as long as you need us.
The stack, so you can hire for it
React Native and TypeScript on the phone. Postgres and Redis behind it. Python, FastAPI, and OR-Tools where the maths lives, React and TypeScript where somebody has to look at the result. Nothing exotic, because you will be hiring against it after we hand over.
