Inbox-driven operations
Carrier updates, customer chases and broker emails all land in one shared inbox.
For shippers, 3PLs and freight tech
Every exception handled before it escalates
Exception summaries, carrier and customer emails, document extraction and dispatcher notes. Keep freight moving and customers informed without drowning your ops team.
Faster exceptions
delays summarised and actioned
Structured documents
BOL and POD fields extracted
Proactive updates
customers hear first
The problem
What is slowing you down today
Documents in every format
Bills of lading, PODs and rate confirmations each arrive looking different.
Customers who hear last
The shipment was delayed at noon. The customer found out at five.
Capabilities
Everything you need, nothing you don't
Exception summaries
Condense the email thread into shipment, issue, impact and next action.
Document field extraction
Pull shipper, consignee, references, weights and dates from document text into JSON.
Customer update drafts
Clear, proactive delay notices in your brand voice.
Carrier email drafting
Tender, follow-up and claim emails from the facts you supply.
Fail-over for peak season
Requests move to another eligible model if one is busy.
Idempotent batch jobs
Send an Idempotency-Key per document so retries are metered once.
Use cases
What teams run on it
01
Control tower summaries
A daily digest of every open exception.
02
Document intake
Structured BOL and POD data for your TMS.
03
Delay notifications
Customer emails drafted the moment an ETA slips.
04
Claims preparation
Organised claim narratives from incident notes and document text.
How it works
From sign-up to production
- 1
Summarise a thread
Paste an exception email chain into the playground.
- 2
Connect your TMS
Call the endpoint from your TMS or visibility platform.
- 3
Scale across lanes
Give each team its own key and watch usage in the dashboard.
Control
Built so you stay in charge
Keys you control
API keys are shown once at creation and stored only as a hash. Revoke any key instantly from Settings.
Spend you can see
Every request carries its own receipt: tokens in, tokens out, latency and price. Nothing is billed that you cannot trace.
Limits you set
Per-account rate limits and a free monthly allowance keep experiments safe before they become production.
Data you decide on
You choose exactly what you send. Repeat prompts can be served from your cache, and cache hits are never billed.
For developers
One endpoint. Every model.
Send a prompt and a capability, or name a model. One bearer key, one small JSON body, and a full receipt on every response.
curl https://YOUR-DOMAIN/api/ainf/inference \
-H "Authorization: Bearer $AI_INFERENCE_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-1042" \
-d '{"prompt":"Summarise this ticket in one line","capability":"chat"}'Questions, answered
Does it integrate with our TMS?
It is a single HTTP endpoint, so anything that can make a web request can use it.
Can it read scanned documents?
It works on text. Send the text of the document, for example from your existing OCR step.
How do we avoid double charges on retries?
Send an Idempotency-Key header per document. Usage for a key is metered once.
How is it priced?
Per token at the catalog price for each model, after a free monthly allowance.
Get ahead of every delay
Summarise today's exceptions on the free allowance.