ShippedLogisticsSupply Chain
// build study

ShipSight

A supply-chain control tower that tracks every shipment across ocean, air and ground, predicts each ETA with a confidence score, and flags at-risk shipments before they slip.

Client:Global shipper (NDA)
Duration8 weeks
ScopeMVP product design and front-end build of the Control Tower board and single-shipment detail experience, backed by an ETA-prediction model, a multi-modal milestone ingest pipeline, and an exception-alerting engine.

// The Control Tower board — on-time, at-risk and avg-delay KPIs above a worst-first table of live shipments across every mode.

// the numbers

Figures from the engagement, shared under NDA.

We publish them unchanged and can’t break them down any further here. The reference build you can open runs entirely on sample data.

3,410Active shipments
87%On-time delivery
42At-risk shipments
1.2 daysAvg delay
01In brief

If you read one part of this page, read these 4 lines.

  • Predicts ETA slips before they happen, not after the carrier scan
  • Unifies ocean, air and ground shipments into one live control tower
  • Flags port congestion and customs holds with a stakeholder alert ready to send
  • Every predicted delay is explainable — weighted drivers, not a black-box date
02Overview

What it does — and which part of it we built.

ShipSight turns a scatter of carrier portals and status emails into one live control tower for a logistics operations team.

It ingests milestones from carriers, ports and EDI into a single timeline per shipment, predicts each arrival with a confidence-scored ETA, and flags at-risk shipments — port congestion, customs holds, weather — before the ETA slips. BuildspaceLabs designed and built the MVP front end — a Control Tower board for network triage and a per-shipment detail view with an inline route map — turning an ETA-prediction model and a stream of multi-modal signals into a workflow a planner can act on in minutes.

03The screens

Every screen here is from the reference build, not the client’s system.

The captions say what you are looking at. Every name and record on them is sample data.

04Outcomes

What the engagement left the client with.

  • Delivered a production-quality MVP of the Control Tower board and shipment detail view in an 8-week engagement
  • Consolidated ocean, air and ground tracking, ETA prediction and exception alerts into a single visibility workflow
  • Gave logistics leadership a real-time view of on-time performance and delay exposure across 3,410 active shipments
  • Established a reusable design system (risk pills, mode icons, route maps, exception bars) for the product's next surfaces
05How it is built

The stack was picked per constraint, not per house habit.

7 technologies across 4 layers — the shape of the stack follows the problem.

AI & ML
Python · ETA model
Frontend & Mobile
Next.jsReactTypeScriptTailwind CSS
Data & Infrastructure
PostgreSQL
Backend & APIs
Kafka + EDI ingest
Every feature in the build (6)
  • Control Tower board with on-time, at-risk, active-shipment and avg-delay KPIs over a status-coded shipments table
  • Predictive, confidence-scored ETA per shipment, recomputed as it moves along its route
  • Exception alerts for port congestion, customs holds, weather and rolled bookings, raised before the ETA slips
  • Inline milestone route map — origin, transshipment, destination and delivery with live vessel position
  • Multi-modal tracking across ocean, air and ground under a single reference — container, trailer and air waybill
  • Delay-driver attribution that decomposes every predicted slip into named, weighted causes
// see for yourself

Don’t take our word for it — it is running in the frame below.

This is the same page the provenance block links to: our reference build for ShipSight, with its own look, copy and motion. Scroll inside it, or open it full-screen.

// more from the lab

A team that ships across the board.

36products in production
8industries served
68+technologies in play

Closest to ShipSight

// next

Building something in this space?

A 30-minute call is enough for us to understand your situation and tell you whether we're the right team. Usable version in the first two weeks if we are.