AI in the platform
Send the mess. Get back a structured order.
Orders reach dispatch as forwarded emails, purchase orders, photos of a dock sheet and spreadsheets somebody maintains by hand. Our platform reads all of it into a structured draft order — locations matched to your saved sites, service, equipment, window, rush flag — and then stops and waits for a human to confirm. That pattern holds everywhere a model touches the work.
Three sentences that govern every model in the system
The model drafts
It reads, extracts, ranks and explains. Every output is a proposal with its source attached.
A person confirms
Nothing is ordered, dispatched, sent or closed until someone with the authority to do it presses confirm.
The engine decides
Vehicle fit, equipment, capacity and cutoffs are settled by deterministic code. A model never decides eligibility.
Order intake
Send it the way it already arrives
Forward the customer's email. Drop the purchase order or the bill of lading. Photograph the handwritten dock sheet. Upload tomorrow's stop list. Or type one sentence. What comes back is a structured draft order with every field traced to the words it came from, and it stays a draft until you say otherwise.
What you can send
-
A forwarded email
Your customers keep writing the email they always wrote.
-
A PDF purchase order or BOL
Attached, or dropped straight into the portal.
-
A photo of a dock sheet
Taken on a phone at the bay door, handwritten and creased.
-
A spreadsheet
Tomorrow's stops, in the file your office already maintains.
-
One typed sentence
"Pickup at our Edison warehouse tomorrow 10am, 6 pallets to Raritan, their dock closes at 3."
What comes back
Draft order
GDX-7712-B · unconfirmed
- Pickup
-
Edison DC — Edison, NJ
matched to your saved site EDI-DC-1
- Delivery
-
Raritan Receiving — Raritan, NJ
matched to your saved site RAR-RCV
- Service
-
Scheduled last-mile delivery
from "tomorrow 10am"
- Freight
-
6 pallets
from "6 pallets"
- Equipment
-
Box truck, liftgate, pallet jack
inferred from pallet count, needs your confirmation
- Window
-
Tomorrow, 10:00 – 11:00
from "tomorrow 10am"
- Receiving cutoff
-
15:00 at the delivery site
from "their dock closes at 3"
In the portal
Paste, type or upload on the New Order screen and watch the fields fill in front of you.
By email
Every account gets its own intake address. Forward a customer order and the draft is waiting in your portal.
Through the API
Post raw text or a document and receive the same structured draft your office would review.
The source document and the draft it produced are both kept on the order, so anyone reviewing it later can see what arrived, what the model made of it, who confirmed it and which fields they changed.
Where else it earns its place
Each of these is a model doing the reading, the ranking or the writing, and a person doing the deciding. The guardrail is written next to the feature because it is part of the feature.
Dispatch copilot
The board ranks who should take a job and says why in a sentence a dispatcher can argue with: "Maria is eight minutes out, already routed past this stop and driving the van with the liftgate. Jamal is closer, but his shift ends before the window." Step away from the board and a short digest tells you what changed while you were gone.
The engine clears who is eligible. The model only orders and explains the candidates it is handed.
Why is this late
Ask any running job why it is behind and get the combination in plain language: traffic on the lane, dwell at the current stop, and what this receiving dock has historically done at this hour.
Every explanation quotes the timestamps and location pings it was built from.
Exception triage
Likely late, failed pickup, refused delivery, tracking lost — each alert arrives with a suggested next action and a drafted customer message: "Your 2 pm pickup is running about 15 minutes behind because of traffic on I-95. New ETA 2:20." One click to send it, one click to rewrite it.
No message leaves the system until a dispatcher sends it, and nothing about another customer can appear in it.
Your account manager, at 2 a.m.
The portal answers the questions people normally phone in: where is my order, what did we ship last week, what does a rush to Newark cost.
Answers are assembled from tool calls against your own scoped data. If the data cannot answer it, it says so instead of composing something plausible.
Claims, incidents and audit drafting
A damage claim or service failure arrives with a drafted root cause and corrective action built from its own timeline: scans, photos, dwell, signatures. Customer audit questions come back summarised, with the evidence pack assembled per control for ISO 9001 and 27001.
A draft is unsigned work. Your operations owner edits and signs it, and every line links back to the timeline entry behind it.
Credential reading at onboarding
A driver or courier partner uploads a licence, a certificate of insurance, motor carrier authority or a W-9, and the platform pulls out the holder, the issuing body and the expiry, flags a name that does not match the application, and puts the reviewer in front of a decision instead of a PDF.
A human reviewer approves every credential. Extraction shortens the reading, not the decision.
Demand and staffing forecast
Volume per service area and per hour, built from your own history. It feeds the driver app's demand map, so the network knows where the work will be before the work arrives.
The forecast is classical statistics on your data. The model writes the note that explains the shape; it does not invent the shape.
Voice in the field
A driver standing at a closed dock taps the microphone and says "arrived, dock closed, security will not sign." It lands as a structured outcome with a note attached, in the seconds it would have taken to unlock a phone.
The transcript is kept beside the structured outcome, and the driver sees what was recorded before it is filed.
What the model is never allowed to do
- Decide whether a driver is qualified, a vehicle is suitable or a window is achievable.
- Create, dispatch, reassign or close an order on its own.
- Send anything to your customers without a person pressing send.
- Invent an ETA, a signature or a scan that no device produced.
- Show one account anything belonging to another.
Your data is not used to train public models, and every model-assisted action is written to the same audit log as a human one, naming the model, the input it read and the person who confirmed it.
What is live, and what is in build
These capabilities reach accounts in stages. Before anything is signed we put in writing which of them is available to you on day one and which is still in build, because a demonstration on your own paperwork should not turn into a feature that quietly arrives later.
What happens when the model reads an order wrong?
The same thing that happens when a person reads it wrong, except earlier: the draft is on screen with each field traced to the text it came from, so the mistake is visible before the order exists. Corrections are recorded against the draft, and they are what we use to improve the extraction.
Can we turn parts of it off?
Yes. Intake, the portal assistant and the drafted customer messages are switched per account. Some companies run intake and nothing else; that is a normal configuration, not a downgrade.
Is the AI deciding which driver gets my freight?
No. Eligibility and assignment rules are deterministic code, and a dispatcher makes the call. The model ranks the candidates that code has already cleared and explains why it put them in that order.
Does intake work with our own system?
Yes. The same extraction is available over the API, so orders your customers send you as documents can be posted to us and come back as structured drafts inside your workflow, not only inside our portal.