01
A model that beats your baseline
A working network on your data, scored against the agreed benchmark before you scale it.
#1 on NetArena MALT (third-party-run)
Your problem,
Custom machine learning
Your problem,
your neural network.
We build custom neural networks end to end — data pipelines, model development and deployment on cloud, edge or embedded hardware — and prove they work on your data before you scale them.
Is it a fit?
A problem worth
a network.
A neural network does two jobs: it recognizes patterns people can’t see at scale, and it compresses a hard decision into something fast and repeatable. If you have a high-volume decision, a sensor or document stream, and a measurable cost for getting it wrong, there is likely a model worth building.
End to endData → model → deployment
Fixed feeCapped per milestone
MeasuredShips only when it beats your baseline
What you receive
A working model, and the means to check it.
Every engagement hands over more than a demo: the model, the pipeline that feeds it, and the harness that scores every version against your baseline.
02
The data pipeline
From raw images, video, documents or sensor streams to model-ready inputs, built to run again every time new data arrives.
03
Deployment where it runs
Cloud, edge devices or embedded hardware, integrated with your systems rather than left in a notebook.
04
The evaluation harness
The harness that scores every version on your data, handed over so your team can re-run it after we leave.
05
Results as measured
A results report on your own data, misses included, plus a go/no-go call at the end of the sprint either way.
06
Deliverables you own
You own the deliverables built for you once paid. We keep our pre-existing tools and license them to you, perpetually, as embedded.
Representative work
Built for real hardware and real data.
Vision on aircraft and loading docks, modeling for physical devices, and research systems for finance.
Vision · Drones
Aerial public safety
Detection networks developed inside a drone-flight simulator, then prepared for deployment on real aircraft for earlier wildfire detection.
Vision · Inspection
Drone-based asset inspection pilots
On-board defect detection on commercial drones with a bolt-on edge computer: consistent standoff capture and before/after comparison between flights.
Vision · Logistics
Warehouse receiving automation
Edge computer vision that reads barcodes and printed labels on inbound pallets, with multi-frame consensus for shrink-wrapped and damaged labels.
Healthcare
Medical-device efficacy modeling
Efficacy modeling for a continuous room-sanitation device, indicating about 80% lower cumulative exposure than spot-cleaning.
Finance
Financial Document API
Cited answers from filings and statements: the figure, its page and table, the calculation and any conflicts.
Quantitative
Quantitative research systems
A nightly research loop that tests one change at a time against the production version and logs every keep-or-revert decision.
Client work is anonymized. Figures come from our own evaluations.
Demos
Drone and vision demos.
Interactive; data anonymized. Open one and click through what a model sees from the air.
AgricultureFlight insights
Tree-by-tree crop-health readings from a public multispectral drone flight over an olive grove.
Open the demo Urban siteSite insightsAn urban development site analyzed from aerial imagery.
Open the demo InspectionRoof inspectionRoof condition across a community building and nearby homes, from drone imagery.
Open the demo PropertyProperty recordsAerial imagery joined to property records for a commercial and industrial precinct.
Open the demoInterfaces
The screens around the model
Sample dashboards and app interfaces we design so people can act on what a model returns.
How we prove it
Measured on your data before you scale.
We agree the metric and the target with you before any build starts, measure your current baseline, and report the results as measured, misses included.
Your answer key
Tested on your own data
Your past decisions and labeled examples are the answer key. The scoping sprint defines the metric that matters and measures your current baseline on them.
Pass criteria first
Agreed in writing
The metric, the target and the comparison with your current process — written down before the pilot starts. A model ships only when it beats your baseline.
A third-party-run result
Measured at volume, in public
One Jump ranks #1 on the third-party-run NetArena MALT leaderboard (100% correctness and safety over 2,500 queries), and we acceptance-test every engagement on the customer’s own data.
A network-policy benchmark, not a finance one.
Record detailsPilots: Acceptance-tested on your own documents before you pay the balance. Fixed fee, capped.
Ways to buy
Start with one decision.
Scale what’s proven.
A fixed-fee ladder. Every rung is priced before it starts, and you decide at each one whether to go further.
STEP 1
Scoping sprint
We audit your data, define the metric that matters and measure a baseline. You get a go/no-go report either way, plus an evaluation harness you keep.
About 2 weeks$20,000–$25,000
- 100% of the sprint fee is credited to a pilot signed within 60 days
- The metric and target, written down
STEP 2
Pilot
A working model on your data, scored against the agreed benchmark — often with a first live demo within weeks.
About 4–6 weeks · fixed and capped$40,000–$75,000
- Acceptance-tested on your own documents before you pay the balance. Fixed fee, capped.
- Misses the target? You get the full results report and the harness, and decide whether to extend
- We never charge beyond the cap
STEP 3
Production
Hardening, integration and deployment to your cloud, your edge devices or your own infrastructure.
Per phaseQuoted in writing
- Each phase is a fixed fee, quoted before work starts
- Change orders are quoted the same way
ONGOING
Retainers
Ongoing support, monitoring and improvements after a pilot or build.
A month · 3-month minimumFrom $2,500
- Essential — $2,500 a month
- Growth — $6,000 a month
- Scale — $12,000 a month
Fixed fees are paid 50% at signature, 30% at a working demo and 20% at acceptance. Pass-through costs, such as compute and labeling, are paid directly by you with no markup.
You own the deliverables built for you once paid; we keep our pre-existing tools and license them to you, perpetually, as embedded.
How it runs
Data, model, deployment — measured at every step.
The same path for a drone, a loading dock or a research desk. You see the scores before each next step.
1. Data
We audit what you have — images, video, documents or sensor streams — define the metric that matters and measure your current baseline.
2. Model
A working network on your data, scored on held-out cases. A new version replaces the old one only when it scores better and breaks nothing that worked.
3. Deployment
Hardening and integration on cloud, edge devices or embedded hardware, with the evaluation harness handed over.
4. Support
Ongoing support, monitoring and improvements after a pilot or build.
Every stage is quoted as a fixed fee, capped at the amount shown in your proposal. Fixed fees are paid 50% at signature, 30% at a working demo and 20% at acceptance. If a stage doesn’t hit its agreed metric, you decide whether to continue.
What happens next
From first message to kickoff.
Every fee is quoted in writing before any work starts.
1. Bring one decision
Send the form below, or book 30 minutes with us directly.
2. A working call
The decision the model should make, the data it runs on, where it needs to run and what a wrong call costs. Mutual NDA by e-signature if you need one.
3. A fixed-fee proposal
Scope, the metric and target, the data we need and the fee cap — in writing before any work starts.
4. Sprint kickoff
50% at signature, then we audit your data and measure the baseline. The go/no-go report follows at the end of the sprint.
FAQ
Questions buyers ask.
Who owns the model?
You own your data and the deliverables built for you, once paid. We keep our pre-existing tools and license them to you, perpetually, as embedded in what we deliver.
What data do we need?
Whatever the decision runs on today — images, video, documents or sensor streams — plus examples of the right call. The scoping sprint audits what you have and tells you, go or no-go, whether it is enough.
What if the pilot misses its target?
You get the full results report and the evaluation harness, and you decide whether to extend. Fees are fixed and capped, and we never charge beyond the cap.
Does the sprint fee count toward a pilot?
Yes. 100% of the sprint fee is credited to a pilot signed within 60 days.
Where can the model run?
Cloud, edge devices or embedded hardware. Our representative work includes on-board detection on commercial drones and edge vision at a receiving dock.
Who pays for compute and labeling?
Pass-through costs, such as compute and labeling, are paid directly by you with no markup.
How is our data used?
Your data is used only to provide the service to you and never to improve it for another customer. Security and procurement material is on the Trust page.
How do we pay?
Sprints and pilots are invoiced and paid by ACH or wire: 50% at signature, 30% at a working demo and 20% at acceptance.
Scope a project
Bring one decision.
We’ll tell you if a model can win it.
We reply within one business day. Prefer a call? Book 30 minutes.