Blog · Published · Updated
AI for engineers: how to test a tool
Short answer
You test AI for engineers on a question with an unambiguous basis in the documentation: the right revision, the unit and the condition of use. A tool that summarises text well can still miss a limit written under a table. At Syntalith team training costs from €1,150 net a day. With 12 people and 1 hour a week saved per person, it pays back in 0.7 months after licences.
- net for implementation for a team of up to 10 people, paid once
- from €1,150
- from start to work of the entire team
- 2 weeks
- after this time, we measure the effect on the same tasks
- 30 days
- conversation with an engineer and a written plan within 2 business days
- €0
We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓
Author: Syntalith · 3 min read
Statistics
AI in engineering work: statistics 2026
0.7 mo.
payback of €1,150 training with 12 people saving 1 hour a week each: €1,813 of time recovered, €214 of licences a month. Scenario.
25.1%
According to a Harvard Business School study (2023) of 758 consultants, tasks within the model's capabilities went 25.1% faster with AI.
14–56%
According to Anthropic (2025), controlled studies found that AI cut task time by 14% to 56%.
Source: Anthropic, Estimating AI productivity gains (2025) ↗
20.0%
According to Eurostat (2025), 20.0% of EU companies with at least 10 employees used AI.
48%
According to the European Commission (2026), 48% of EU SMEs and mid-caps name a lack of expertise as a barrier to AI.
Source: European Commission, Flash Eurobarometer 578 (2026) ↗
Figures checked: 22 October 2026
An example: a range with two limits
First settle whether the team needs help with reading documentation, with code or with design work. For the trial, choose an approved specification and a question the engineer knows the answer to. Record the document, the revision, the page and the passage with the condition.
Suppose a practice data sheet allows the device to run from 5 to 35°C, and only under the stated installation conditions. The question concerns a location where the temperature drops to 3°C. A good answer gives the range, points to the installation conditions and states that 3°C falls outside the sheet. A weak one gives only „up to 35°C” or leaves out the condition. Then remove the page with the installation conditions. The right behaviour is to point out the missing material.
- 01Questionthe engineer knows the answer and the source passage
- 02Answerthe range, the unit and the condition, with the page number
- 03Removed pagethe AI should point out the missing material
- 04Assessmentreading errors, missing material and interpretation errors scored separately
| Control question | What to record with the result |
|---|---|
| Was the right revision used? | the document reference and date |
| Were the unit and condition kept? | the source passage next to the answer |
| Is missing data visible? | the information that could not be established |
| How much work does checking take? | the time from the question to a checked finding |
What AI training for engineers costs and when it pays back
- Time saved
- 12 people × 1 h a week × 4.33 = 52.0 h
- Value of that time
- €1,813
- Licences
- $240 (€214)
- Left after licences
- €1,599 a month
Payback of €1,150 training
0.7 months
The hours saved are the scenario's assumption, which we check by timing the tasks before the training and after 30 days. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Claude Team licences at $20 per person a month, at the ECB rate of 1.1205 USD per euro on 22 October 2026.
We measure the hours in the scenario before the training and after 30 days, on the same team tasks. If after a month checking AI-written text takes as long as writing from scratch, we change the exercises or the scope of the tool.
According to a Harvard Business School study (2023) of 758 consultants, tasks within the model's capabilities went 25.1% faster with AI. In the same study, results with AI were worse on tasks outside that range. So the exercise teaches people to recognise which documentation questions the model can handle and which need a reading of the source.
A drawing needs its own check
Readable text in a PDF and relationships shown on a drawing are different tasks. Finding a device label does not confirm that connections, dimensions and annotations were recognised. Comparing drawing versions is best done in the design tool. Autodesk describes Activity Insights in AutoCAD together with a limitation for layers that are off or frozen in the current drawing. Concept material is assessed differently, as AI for architects: comparing design options describes.
Reading specifications and standards
an assistant that quotes the page and the revision
team training
Comparing drawing versions
a feature of the design tool
no extra AI
Documentation may not leave the company
a local model on the company's server
private LLMs
Where to start
A specialist who knows the documentation assesses the trial. Bring two data sheets to the workshop and five questions the team knows the answers to. We run the workshop as part of team training. For the free process review, a description of one task the team does every week and the tools it uses is enough. You get the training programme in writing within 2 working days.
„I already use AI.”
Your people too. Just no rules.
From our conversations with companies
5 na 10 employees paste sensitive data into private AI accounts: contracts, invoices, customer data.
In ESET survey (2026)
1 na 10 admits this in the survey.
Customer data pasted into a private AI account without an data processing agreement is a violation of the GDPR.
Don't worry, we won't tell anyone :)
What do we see in companies that "already use"
- Only ChatGPT or Claude accounts, without plugins, skills, integrations and MCP servers with company tools.
- Company programs are not connected to AI. People still click through systems and Excel, and enter chat data manually.
- Lack of company standards: everyone writes instructions in their own way, no one shares what works.
- No rules for personal data, GDPR and company secrets.
- No limits and no visibility: no one knows who uses AI, how much and for what.
62% Polish employees use AI at work · 27% companies have written rules for working with AI.
Source: ESET and DAGMA, Cyberportrait of Polish business 2026 (March 2026, 1,026 people) ↗
ChatGPT or Claude space review
Accounts, permissions, rules for working with data and 5 tasks set for the team. 1 day.
€450 net
Company accounts, rules of working with data and team training in 2 weeks, from €1,150 net.View implementation for the team →
„Is my data safe?”
Yes. You choose where they go: from your company account to the model on your server.
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.
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.
02API with zero retention (ZDR)
The provider processes the request and does not save anything. It requires his consent, we prepare the application together.
03Processing in the EU
Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.
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 Your examples
- 2 tuning
- 3 test on new cases
- 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 →
Price
Three packages. You know the price right away.
Team of up to 10 people
from €1,150
net, paid once · 2 weeks
Company, from 11 to 40 people
from €2,300
net, paid once · 3–4 weeks
Organization, over 40 people
from €4,600
net, paid once · 6–8 weeks
- The same packages once you have licenses. To start, an inspection of the space in 1 day is enough: €450 net.
- You buy Claude Team licenses directly from Anthropic, without our markup: USD 20 per person per month for annual payment or USD 25 for monthly payment, from 2 to 150 people.
From conversation to measurement
01 · 30 min
Free process review€0
An engineer picks 3 to 5 of your team's tasks with you. Written plan within 2 working days.
02 · 2 weeks
Rolloutfrom €1,150
Accounts and roles, rules for working with data, training on your team's tasks. You buy licences directly from the provider.
03 · after 30 days
Measurementincluded
We compare task times before and after. We name in writing the tasks worth handing to a system.
or call+48 888 78 48 78WhatsAppMon–Fri 9:00–17:00 CET
Worked example · Scenario
How we count the payback: technical documentation
We run the same count for your team in the free process review.
€3,490
a month for writing the reports for 400 jobs
Payback: 1 mo.
15 minutes to write a work report 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 a photo at €0.0042 (0.004734 USD), measured in our field documentation system, plus the description (Claude Sonnet 5.5, about 2,000 + 400 tokens), at the ECB rate of 1.1205 USD per euro on 22 October 2026.
See the full calculation →Questions
How do you choose AI for engineers?
First settle the task: reading documentation, code or design. Then test the tool on a question with an unambiguous basis: the right revision, the unit, the condition of use and missing data shown openly.
Does AI read technical drawings correctly?
Reading text from a PDF is easier than reading relationships on a drawing. Finding a device label does not confirm connections or dimensions, so you check the drawing separately, ideally in the design tool.
How much does this training cost?
At Syntalith from €1,150 net for a day of workshop for the team. Claude Team licences cost $20 per person a month. With 12 people and 1 hour a week each, the payback is 0.7 months.
Who approves AI output in documentation?
The qualified engineer responsible for the document. AI helps with reading and comparing, and calculations and design decisions stay with the specialist.
