Skip to content

Blog · Published · Updated

Subiekt and AI: how to prepare the integration

Short answer

You start an AI integration with your sales software from the document that should be created and the work needed to prepare it. Reading an order from an email is not enough: the client, product, unit and way of writing the record must be recognised. The first scope can end with a proposal a salesperson checks. An automation costs from €3,000 net and, at 800 orders a month of 6 minutes each, pays back in 1.3 months.

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 · 3 min read

Example: the morning request inbox
Agent · ready

Statistics

Trade and automation: statistics 2026

1.3 mo.

payback of a €3,000 automation at 800 orders a month: €2,792 of work today, €565 with checking and the model. Scenario.

Figures checked: 22 October 2026

Prepare a small product list for the trial

In a sample order, the client writes „two packs of seals”. The product list holds packs of ten and packs of twenty. Reading the number two is correct, but it settles neither the number of units nor the product. The result shows a gap to clarify before a sales document is created. For the trial, choose a few items where the salesperson knows the correct result: the product code, the unit and the names clients use.

Give the supplier the full name of the program version, the installation type and the add-ons you have, and the administrator confirms the available way of exchanging data. The vendor describes the extension mechanism in Subiekt nexo PRO and a separate add-on for Subiekt GT. The vendor's description of what is possible does not prove that a supplier's connector will handle your installation and every field.

Acceptance stageWhat the reviewer sees
Reading the messagethe data beside the source passage
Matchingthe item chosen and the differences still open
Commercial checkthe price and terms from the agreed source
Writethe document type, its ID and the result of the operation
Retrywhether the earlier write already happened
From an email order to a document
  1. 01Readingclient, items, quantities and units with the source passage
  2. 02Matchingthe product from the list and the pack conversion
  3. 03Gapa question to the client for an item with no conversion
  4. 04Approvalthe salesperson checks the proposal
  5. 05Writethe document in the agreed state, with its ID

What it costs and when it pays back

Scenario: 800 orders a month
Today
800 orders × 6 min = 80 h (€2,792)
With the system, a person checks the output in 20% of the time
€558
Model, 1 call per case, Claude Sonnet 5.5
€6
Cost of one case
€3.49 today, €0.71 with the system
Saving
€2,227 a month

Payback of €3,000

1.3 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: 2,500 input tokens and 400 output tokens per call at Anthropic's rates, at the ECB rate of 1.1205 USD per euro on 22 October 2026.

The count covers the work around a case: searching, reading, writing and handing over. What remains is the time to check the result, 20% of today's work in the scenario. Before the quote, we measure both times on 20 to 100 cases the team has already handled, in a free test that takes 5 working days.

An item with no conversion needs a person to clarify it with the client. We record the question beside the order, so a colleague covering the work knows what the team is waiting for, and the client's answer does not quietly overwrite the earlier version.

When an import is enough

If the client can send product codes in a structured file, check the import in your program before you build reading with AI. With messages in mixed forms, compare the model's proposal with matching by hand, and treat units and packs as a stage of their own. Creating an order does not have to mean a reservation, fulfilment or an invoice, so describe the effects of the write with the person who looks after the program. If the program feeds an online store, check how the connection handles reservations, as described in stock checks for an online store.

Import, a proposal or a write
  • Clients send product codes in a file

    the program's import

    configuration

  • Orders from emails in different forms

    a proposal for the salesperson to approve

    from €3,000

  • Proposals checked, time for the write

    a write after approval with a check on retries

    priced as a separate change

Where to start

For the call, the program version, the order type and an example of an unclear entry in the product list are enough. The cost of the vendor's module and of your own integration is set out in the price guide, and the scope is described in automating order preparation. We build this kind of rollout as part of AI automations. For the free analysis, a description of one case from recent weeks and of the tools it passed through is enough. You do not need to send confidential documents, and you get a written plan within 2 working days.

Worked example · Scenario

How we count the payback: preparing orders

We run the same count for your orders in the free analysis.

€2,443

a month for handling 600 orders by hand

Payback: 1.4 mo.

7 minutes to retype an order into the software 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 order in our system (about €0.0006) plus matching the lines (Claude Sonnet 5.5, about 3,000 + 500 tokens), at the ECB rate of 1.1205 USD per euro on 22 October 2026.

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 do you prepare an AI integration with sales software?

    Settle the program version and its add-ons, choose the target document and its state, prepare a product list with correct results, and split acceptance into reading, matching, the commercial check, the write and a retry.

  • Can AI create documents in the sales software on its own?

    It can after a salesperson approves. The first scope usually ends with a proposal, and we price the write as a separate change, which makes offers easier to compare.

  • How much does such an automation cost?

    At Syntalith from €3,000 net. At 800 orders a month of 6 minutes each, the payback is 1.3 months. We agree integrations and maintenance before the quote, and the model costs €6 a month.

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.