The archive · Logistics & Supply · Product decision · 2026
Transload bets CCTV can measure every LTL shipment: YC P26, HN launch, ~$50K/site/month
Three TU Munich friends turn warehouse security cameras into freight dimensioners, so LTL carriers catch underbilled shipments without slowing the dock.
transload
What the business is
A software company that turns the security cameras already installed in freight terminals into automatic dimensioners, measuring every LTL shipment as it moves through the normal dock workflow with no new hardware.
How it started
The three founders - Nils, Julius and Jago - studied together at TU Munich and had known each other for eight years when they started transload in 2026. Jago grew up around the industry through his family's LTL trucking and cross-docking business. Their first idea was AI for optimizing forklift routes inside cross-dock terminals, but after talking to more than 50 trucking companies they kept hearing about freight dimensions instead - and realized that recent advances in monocular metric depth estimation made it possible to recover accurate 3D structure from ordinary camera footage without LiDAR.
What happened
The company joined Y Combinator's Spring 2026 (P26) batch and launched publicly on Hacker News on June 8, 2026, then on Launch YC on June 21, 2026. Its two-step system connects a barcode scan timestamp to the correct shipment in video - reasoning over gaze, body orientation and movement - then segments the object and estimates a metric 3D bounding box, reporting under 1.5 inches of mean absolute error today. The founders say they are working with several LTL carriers, with one customer showing dimension errors on roughly 10% of checked shipments, and claim catching those differences is worth about $50K per site per month.
How it ended up
Live with pilot customers and scaling the measurement itself: the team says its focus is pushing bounding-box accuracy below one inch at full coverage, with the first paid use case being revenue recovery - identifying under-dimensioned shipments and correcting billing - before moving on to trailer-utilization optimization.
Background
transload is a San Francisco startup, founded in 2026 by three friends from TU Munich - Nils (computer vision), Julius (ex-McKinsey) and Jago (AI on industrial sensor data) - that measures LTL freight with the security cameras already hanging in trucking terminals. The bet: carriers lose billions because they price by volume but trust shipper-declared dimensions, and the fix is software that measures every shipment invisibly, not another dimensioning station that slows the dock.
The founders did not start with this idea. Their first concept was AI for optimizing forklift routes in cross-dock terminals, but after talking to more than 50 trucking companies they kept hearing about the same pain: understated freight dimensions. Jago grew up around the industry through his family's LTL trucking and cross-docking business. Meanwhile spatial AI had just crossed a threshold - monocular metric depth estimation improved dramatically - making it possible to recover 3D structure from ordinary cameras without LiDAR.
transload's system links each barcode scan to the right object in video around the scan timestamp, then fits a metric 3D bounding box from one camera view; the founders report under 1.5 inches of mean absolute error today. Terminals already run fixed cameras, repeated workflows and barcode scans, so the measurement happens in the background with no new hardware and no change to dock processes. Its YC profile claims 15% of shipments turn out bigger than declared, worth about $50K per site per month in rebillings and trailer utilization.
The company joined Y Combinator's Spring 2026 batch, launched on Hacker News on June 8, 2026 (56 points and 19 comments) and on Launch YC on June 21, 2026, and says it is working with several LTL carriers, with roughly 10% of checked shipments showing dimension errors for one customer. Its stated first use case is revenue recovery - identifying under-dimensioned shipments with visual evidence so carriers correct billing - before moving on to trailer-utilization optimization.
What has to be true
- Dimension fraud or error is measurable and recurring: every understated shipment is lost revenue, so the customer can calculate payback per terminal before buying.
- Existing CCTV removes the adoption hurdle: no forklift travel, dock congestion or new workflow, which is why dedicated dimensioning stations only sampled freight.
- The technical threshold just moved: cheap monocular metric depth made accurate 3D measurement from ordinary cameras possible without LiDAR hardware.
- A narrow wedge keeps focus honest: revenue recovery from underbilled LTL shipments is a pain the founders verified across 50+ trucking company conversations.
What can be applied
Pick the pain customers mention in every conversation, then reuse assets they already own: no new hardware made the sale to terminals possible.
Aftermath
As of September 2, 2026, transload is live with pilots: its YC profile (Spring 2026 batch) reports that 15% of its customers' shipments turn out larger than declared, worth about $50K per site per month in rebillings and trailer utilization, and per its Hacker News launch it works with several LTL carriers, one showing roughly 10% dimension errors on checked shipments. The three-person San Francisco team is focused on measurement accuracy, targeting under one inch of mean error at full coverage.
Sources
- Launch HN: Transload (YC P26) - Measuring freight items with CCTV
- Launch YC: transload - we measure freight with security cameras
spotted an error? The archive wants to know.
Your turn
You just read one. Describe what you are building, and see who is betting on the same thing.
Free account · 3 free questions · no card