Bots, email and document processing, calculation pipelines and integrations. We started with our own wholesale business — now we automate client processes across many industries.
Not a platform and not a box: we come into your processes as they are and take the manual work out of them.
They answer customers, notify the crew and the managers, pull reports together and draft follow-up letters. Scripts and integrations are our words to worry about, not yours.
Incoming mail is machine-read: enquiries, invoices and statements land where they belong by themselves. AI reads the scans and drawings a person used to sift through.
Cost prices from documents, recommended sale prices, data gathered for decisions — minutes instead of days, with a human checking the draft.
We connect what you already use: CRM, spreadsheets, messengers, accounting. If you ever accidentally learn the word «webhook», we have slipped up somewhere.
01 / Explore
This sample order shows how our running delivery workflow works. The retailer, product and quantity are fictional.
01 / Input
In the running workflow, orders arrive through EDI. The system reads line items, quantities and delivery dates, preserving the link to the original order.
A person handles exceptions: an unknown product, a disputed quantity or an order change.
Incoming order / example
Source retained
02 / Shared record
Line items are matched with the accounting system. The order, register entry and upcoming shipment are linked together.
The person responsible agrees the matching rules. Unrecognised items need clarification.
Order record / example
No duplicate entry
03 / Retailer rules
The required documents depend on the retailer, product and delivery terms. The workflow selects files and generates labels from the order data.
A specialist defines the requirements. A missing source calls for a review, not a guess.
Document pack / example
Contents listed
04 / Human decision
The record and document pack arrive in the team chat. The person responsible sees what was assembled and checks the data before use.
Automation removes data transfer work. A specialist remains responsible for document contents.
Team chat / example
Order AXM–DEMO–104. Document contents and source data are available in one record.
Reviewed by a person
05 / Next part of the workflow
Documents and shipment details stay linked to the register. They can then support checks on deliveries, pallets and settlements.
Your workflow may be different. We agree its boundaries first, then adapt this approach to your operations.
Register / example
History can be checked
06 / Reconciliation
Shipment details are compared with the register and bank statement. In this sample, the payment differs from the shipment amount: the discrepancy appears alongside its sources.
A difference does not yet establish a debt. The person responsible checks the payment reference, documents and adjustments, then decides what to record in the accounts.
Reconciliation register / sample amounts
Review by the person responsible required
The amounts are fictional. This example creates no accounting entries and makes no changes to the accounts.
This is a workflow illustration, not a connection to live orders. It uses no client data and sends nothing.
The bots work inside your chats and CRM, while the full picture lives in the AXM dashboard. The costing queue: the robot has read the drawing, costed the part and says plainly how confident it is. The costing card: the manager edits material, operations and quantity, and the total recalculates as they type. The correction is kept as a reference for similar parts, and a multi-item deal shows its grand total straight away.
The rate book holds operation rates and material prices; some of those prices the robot pulls from metal traders' public price lists and tags with where and when they came from. Roles and permissions depend on the project type: a costing project and a wholesale one get different sections. AI spend is tracked per project, by operation and by model. The screenshot here is a made-up client: real queues are seen only by their owners and the people the owner lets in.
For suppliers to retail chains: the document pack for every shipment is put together to each chain's rules, not from a manager's memory.
Every chain has its own demands: some want quality certificates and declarations of conformity, some want inspection certificates and a power of attorney, and some check the pack when the goods arrive. The rules live in the dashboard, where you can see and correct them; the pipeline puts into the pack exactly what the rules say.
A storage-conditions reference — temperature, humidity and shelf life for each crop — with the GOST standard each entry came from and how confident we are in it. Your quality specialist signs it off; when a chain sends no requirements of its own, the conditions go from here onto the label.
Labels and shipping documents are built from the database, not from stale templates: the barcode, the case quantity and the pallet configuration come from whichever source is assigned to that chain.
Every delivery note in one register, with analytics on top: how many pallets went to each chain in a week, a month or since the season began, and where shipments dipped.
The robots run on your server or on ours, whichever your security people prefer. What access to mail, CRM and spreadsheets is needed, we agree up front and write down: what we read, what we write, what we leave alone.
The dashboard never touches your CRM, mail or accounting system: the robots publish data snapshots, and the screen shows when a snapshot was taken. Edits made in the dashboard — rates, chain rules, corrections to a costing — go into separate tables the robots pick up on their next pass, and every action is logged.
Neural networks read drawings, scans and emails, cost the parts and draft replies — that is an external model, and what it gets to see we agree up front. Everything else is ordinary code, no magic: it behaves the same every time and leaves a trace in the log. A person signs off the robot's draft.
03 / Evidence
Our automation grew out of wholesale fresh-produce deliveries. It is a running workflow with orders, accounting, documents and people in team chats.
In operation
EDI order intake, document-pack assembly, shipment records and register links are automated.
04 / Getting started
We inspect the input, result and exceptions. We agree who approves the data and how to tell whether the process has improved.
We record what we read, what we change and which data may be shown to an external model. We test within a limited scope.
We train the people responsible and provide an action log and an error-handling procedure. Support terms are agreed in advance.
Tell us what data you transfer, from where and to where. That is enough for the first conversation.
Discuss your process