Skip to content

Blog · Published · Updated

AI in trade: units and packs in an order

Short answer

AI in trade reads an order from a message or an attachment, but the quantity has to stay tied to its unit: „10” can mean units, cartons or sets. Before a line is saved, an employee sees what the client ordered and where the conversion to the order system's unit comes from.

How we workDetails ↓

  1. 01Call30 minutes with an engineer, free
  2. 02PrototypeA working system on your process and data, free
  3. 03ImplementationTarget and fixed price in the contract; 50% at signing
  4. 04Acceptance50% once the agreed target is met
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000

We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓

Author: Syntalith · 4 min read

Example: the morning request inbox
Agent · ready

Statistics

Trade and AI: statistics 2026

1.2 mo.

payback of €3,000 at 1,500 orders a month: €3,490 of work today, €1,056 with checking and the model. Scenario.

Figures checked: 22 October 2026

An order line with its unit
  1. 01The client's wordingthe quantity and the unit from the message
  2. 02Productthe client's item code matched to the product
  3. 03Conversionunits per pack, with its source
  4. 04Linethe quantity in the system's unit
  5. 05Approvalby an employee before saving

The product name does not tell you the pack size

In a fictional order, a client asks for 10 cartons of product A. The current product record says 12 units per carton. The result is 120 units, as long as the record really covers the variant ordered. If a similar product B has 24 units recorded, that number cannot be used to convert A.

GS1 US distinguishes packaging levels, including the single unit, the inner pack and the case. The description shows why a product code should be tied to the way it is packed. It does not mean that every supplier uses the same number of units. Packaging level definitions, checked on 9 October 2026.

If the order says only „10 packs” and the company handles several pack sizes, leave the line for clarification. The client's answer should go into the case, so the warehouse does not have to reconstruct the agreement again.

If a wholesaler accepts item codes assigned by its clients, check the buyer first. The same code can mean a different product at two companies, and a change of the assigned customer requires the line to be assessed again. The client's item code is matched before the unit and the conversion are checked.

Keep the original wording before the conversion

Next to the draft line, show the source text, the product code, the unit ordered, the conversion and the result in the stock unit. A final number on its own makes it hard to judge whether a mistake came from reading, matching the product or multiplying.

Data in the exerciseResult to check
10 cartons of 12 units120 units, with a reference to the product record
10 packs, size unknownA question about the type of pack
New product record: 8 units per cartonA decision on which orders the change applies to

Do not overwrite a historical conversion with a new one only because the product record changed. The process owner should decide which terms apply to an order already accepted. The table above is an exercise, with no integration running.

When do you need a model?

With a tidy file and agreed codes, an import and a conversion rule are enough. AI can help extract data from messages written in many different ways. Saving to the order system, spotting a repeated order and handling a correction need further rules; reading one email correctly does not prove they work.

Before you build, check the features of the sales system you use. If the difficulty is the supplier's later reply, a separate guide covers comparing an order with its confirmation.

Once the conversion is agreed, you still have to choose the document type in the order system and check what creating it sets off.

On the purchasing side come the labels suppliers use. Keep global unit synonyms apart from names assigned to a supplier and a product. Recognising the word „shrink pack” still needs a separate confirmation of the number of units in the pack.

A correct conversion then has to be tied to the document, the reservation and the agreed stage of fulfilment.

Syntalith builds automations. A possible first scope is a list of lines for approval, with the source and the conversion visible. We price the integration with the system and the cases of ambiguous packs after reviewing the materials. Syntalith prices: an automation, app or agent from €3,000 net, training from €1,150 net a day (pricing). It is enough to describe an order that recently came back from the warehouse for correction.

What it costs

Scenario: 1,500 orders a month
Today
1,500 orders × 4 min = 100 h (€3,490)
With the system, a person checks the result in 30% of the time
€1,047
Model, 1 call per case, Claude Sonnet 5.5
€9
Cost of one case
€2.33 today, €0.70 with the system
Saving
€2,434 a month

Payback of €3,000

1.2 months

The volume, the time and the checking share are the scenario's assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Model: 2,000 input tokens and 300 output tokens per call at Anthropic's rates, at the ECB rate of 1.1205 USD per euro on 22 October 2026.

What we measure in the trial
  • The time from receiving a case to the result, before and after the change
  • Cases the application passed to a person
  • Corrections by the person checking
  • The cost of the model and maintenance at the target volume

Where to start

In the free review we choose one process and count the volume and the team's working time, and within 2 working days you receive a written summary with a price. We build the automation as part of AI automations, from €3,000 net.

Worked example · Scenario

How we count the payback: orders at a wholesaler

We run the same count for your wholesale business in the free review.

€3,490

a month for quoting 150 enquiries by hand

Payback: 1 mo.

40 minutes to quote a request and checking in 15% of the old time are our assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat, for companies with 10 or more employees. Model cost: reading the enquiry in our quoting system (about €0.0008) plus pricing the lines (Claude Sonnet 5.5, about 4,000 + 1,500 tokens), at the ECB rate of 1.1205 USD per euro on 22 October 2026. The extra margin is a scenario: we assume 1 in 40 enquiries quoted the same day ends in an order that a slow reply loses today, with a margin of €344. In the review we count it on your sales process.

See the full calculation →

This is how we implement it in companies

All case studies →

Client results.

All projects →
foap.comcustomer service

foap.com customer service: 95% of replies are sent automatically.

Users from several countries write to foap.com, in several languages. The system reads the entire conversation and the terms of that person, and then sends a response in that person's language. Questions about money and exceptions go to the team with a ready draft, so they have to check and send them.

the system sends the answers itself, without human typing
95%
time from the arrival of the e-mail to the ready response (median)
30 s
e-mails that require a response receive a ready-made draft
100%
less work for every 1000 answers (estimate)
47 h

Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.

How foap.com customer service works →
Sample messages. Money matters always come to the person.

Other implementations

jaktako.design

studio projektowe

−87%

Time to look for new customers, every day

4 hours → 30 min

approx. 73 hours less per month (21 days of work)

according to the studio

How the agent loop works →
Signature Estates

real estate

approx. −90%

Operator time spent browsing portals, per day

2–3 hours → 20 min

approx. 45 hours less per month (21 days of work)

respect · contact the seller 5 minutes after the announcement

How the agent finds property listings →
Kuba Koziej, CEO and co-founder of MoreGrowth and board member at Natu.Care

Kuba Koziej

CEO and co-founder, MoreGrowth

„We started with my own AI agent. During the training that followed, I learned to build new applications myself. Today I am bringing this way of working with AI into my business. Working with Syntalith gave me exactly the skills and tools I needed.”

View the original training review on LinkedIn ↗

Start with the process that takes the most time each week.Book a free process review (30 min) →

How we build automation and agents

From a conversation to a working system in four steps.

  1. 01 · 30 min

    Free process review

    €0

    You're talking to an engineer. You receive the written plan within 2 business days.

  2. 02 · 5 days

    Free prototype

    €0

    The system works on 20-100 cases that your team has already handled. You see every result.

  3. 03 · 2–16 weeks

    Build

    50%

    Fixed price and goal written in the contract. First installment upon signing.

  4. 04 · after reaching the goal

    Reception

    50%

    You pay the second installment when the system reaches its target on your cases.

How a free prototype is created

Mon.

We set a goal

What result do you consider good?

Tue–Wed

The system is working

It goes through your affairs, one by one.

Thu

We compare

We check every difference with the team's work.

Fri

Result and price

List of errors and fixed implementation price.

You choose the matters. We anonymize them upon request, they stay in the EU and we delete them after the test.

On the market, such a test usually costs from PLN 3,000 to PLN 8,000.

Book a free process review (30 min)

We establish a prototype during a free analysis.

Data checked on October 21, 2026.

„Is my data safe?”

Yes. You choose where they go: from your company account to the model on your server.

  1. 00Employee's private account

    Customer and company data ends up in an account that the company cannot see or control. There is no data processing agreement, so it is a violation of the GDPR. When an employee leaves, the chat history goes with them.

  2. 01ChatGPT or Claude corporate account

    The provider does not use your data to train models. A copy of the queries remains in his logs for up to 30 days.

  3. 02API with zero retention (ZDR)

    The provider processes the request and does not save anything. It requires his consent, we prepare the application together.

  4. 03Processing in the EU

    Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.

  5. 04Model at your place

    The open model runs on your server or in your cloud in the EU. The data does not go outside the company.

What we do with every implementation

  • Confidentiality agreement and data processing agreement before we receive any data.
  • You choose the cases for the prototype and we anonymize them upon request.
  • The data stays in the EU and we delete it after the test.
  • Corporate accounts with an administrator on your side.

When data cannot leave the company

The open model runs on your server or in your cloud in the EU. To choose from:

White-tailed eagle
Polish model, SpeakLeash and ACK Cyfronet AGH
PLLUM
Polish model, HIVE consortium commissioned by the Ministry of Digitization
Qwen
Alibaba
GLM
Zhipu AI
DeepSeek
DeepSeek

We select a model for the task and check it on your cases. We run it, tune it and maintain it.

Source: Bielik and PLLuM, ACK Cyfronet AGH ↗ · PLLuM, Ministry of Digitization ↗

Do you have a lot of your own data? We will fine-tune the small model.

  1. 1 Your examples
  2. 2 tuning
  3. 3 test on new cases
  4. 4 model at your place

When you have thousands of similar emails, documents or reports, we teach a small open model based on your examples. It works for you, responds quickly and costs less to maintain than a large model. We measure quality on issues that the model has not seen while learning.

Przemysław and Piotr did it in large programming and consulting companies. Artem did it before and does it today at Syntalith. It's about models on your own infrastructure, tuning and quality measurement.

You choose the protection level during the interview. We sign the data processing agreement before we see any data.Schedule a free analysis →

AI implementation

Start with the process that takes the most time each week.

The engineer chooses one process with you and calculates how much it costs today. Then we build a free prototype on 20-100 cases that your team has already handled. We write down the goal and the fixed price in the contract.

See AI implementation →
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000

Questions

  • How does AI read quantities in orders?

    It keeps the quantity together with the unit from the client's order and shows the conversion to the system's unit with its source. An employee approves the line before it is saved.

  • When do you need a model, and when is a rule enough?

    With a tidy file and agreed codes, an import and a conversion rule are enough. A model helps with client messages written in many different ways.

  • How much does it cost?

    At Syntalith, AI apps, automations and agents start from €3,000 net. At 1,500 orders a month and 4 minutes each, the payback is 1.2 months.

Let's talk

Just write, call or choose a date.

We work fast because we hate corporate cotton wool. We don't have salespeople or managers to keep an eye on managers. You talk immediately to engineers who then build your system. We respect each other's time and yours too.

We will accept 3 more companies by the end of the year.

Mon–Fri 9:00–17:00 CET

What our OpenAI and Anthropic partnerships mean for you.

OpenAI makes ChatGPT and Anthropic makes Claude. We belong to the partnership programs of both companies, so we work with their tools every day and learn from the creators themselves.

OpenAI Select PartnerClaude Partner Network
01We will select a tool for the task
We implement both ChatGPT and Claude. We check both on your documents, and you choose the one that makes fewer corrections and saves more time.
02Knowledge straight from the creators
We learn from official OpenAI and Anthropic courses and materials. Your team learns about the features and settings that work today.
03Licenses without our margin
You buy accounts directly from OpenAI or Anthropic and receive an invoice from them. We do not add anything to the license.
04Certified engineers
On the team, we have an AWS certification in machine learning and an Anthropic certification in systems architecture on Claude.

Participation in programs does not mean that OpenAI or Anthropic endorses our services.