Blog · Published · Updated
AI in construction: a list of document changes
Short answer
AI in construction prepares a working list of changes in the documents: what changed, which document and revision the item concerns, and who should check it. The designer decides what a change means, and drawings are best compared in the design tool. At Syntalith team training costs from €1,150 net a day. With 10 people and 1 hour saved a week each, it pays back in 0.9 months after licence costs.
- 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
Construction and AI: statistics 2026
0.9 mo.
payback of €1,150 training with 10 people saving 1 hour a week each: €1,511 of time given back, €178 of licences a month. Scenario.
10.8%
According to Eurostat (2025), 10.8% of EU construction companies with at least 10 employees used AI, the lowest share of any sector surveyed.
Source: Eurostat, use of artificial intelligence in enterprises (2025) ↗
20.0%
According to Eurostat (2025), 20.0% of EU companies with at least 10 employees used AI.
Source: Eurostat, 20% of EU enterprises use AI technologies (2025) ↗
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.
32.7%
According to Eurostat (2025), 32.7% of people aged 16 to 74 in the EU used generative AI tools in the previous 3 months.
Figures checked: 22 October 2026
Before you compare content, settle the pair of documents
Choose two versions of the same document and record their designations. The date an attachment arrived can differ from the revision date, and a newer email can carry an older file. When versions are not labelled, start with a register: AI will not settle which file called „final” the designer approved.
A designer's comment says the label of a device changed on a drawing. The list prepared with AI points to that place, the document number, the revisions compared and a question: does the change of label require an update of the bill of materials? The person who runs the documentation assigns the question to the engineer from that discipline. After the decision, the list keeps the link between the comment, the clarification and the decision, so whoever takes over the item understands why it was closed.
- The document number and the revisions compared
- The place of the change and the source of the description
- The question to settle and the person responsible
- Status: to check, clarified, closed with a decision
AutoCAD compares the current drawing with an earlier version through Activity Insights, when the subscription and storage requirements are met. Use the graphic comparison during the review, and give AI the draft description based on the approved comments.
What AI training for construction teams costs and when it pays back
- Time saved
- 10 people × 1 h a week × 4.33 = 43.3 h
- Value of that time
- €1,511
- Licences
- $200 (€178)
- Left after licences
- €1,333 a month
Payback of €1,150 training
0.9 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 a 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 tasks of the team. If after a month checking texts written with AI takes as long as writing from scratch, we change the exercises or the scope of the tool.
On a construction project, the hour a week comes from descriptions of changes, minutes of coordination meetings and questions to the engineers. The expensive item is a change someone missed because it came in an email with an older file. So in the exercises we count the items where the list correctly flagged a missing revision or a repeated attachment.
A test before documents are fetched automatically
Prepare a small set of materials: a correctly labelled change, a file with no revision and a resent attachment. Check that the list keeps the question for the file with no revision and does not duplicate the item for the repeated attachment. This is a proposed way to accept the work: this article did not measure how drawings are read. Training for engineers covers comparing versions, describing changes and passing questions to the disciplines. Fetching documents automatically from email and shared folders is the next step, once the team has checked the list on hand-picked files.
Versions are not labelled
a register of documents and revisions
no build
The team describes changes and questions with AI
training for engineers
from €1,150
Hundreds of documents from several disciplines in email
an app for change lists with sources
from €3,000
Where to start
In the first project we limit the scope to one type of document and one design team. We run the workshop as part of our 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 receive the written training programme 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: AI in construction
We run the same count for your team in the free process review.
€3,490
a month for quoting 50 enquiries by hand
Payback: 1 mo.
2 hours to quote an enquiry with a bill of quantities 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 100 enquiries quoted before the deadline ends in an order that a slow reply loses today, with a margin of €3,442. In the review we count it on your sales process.
See the full calculation →Questions
How does AI help with changes in construction documents?
It prepares a working list of changes: the document, the revisions, the place of the change, the source of the description and a question for the right person. The designer assesses what the change means.
Will AI compare drawings?
Drawings are best compared in the design tool, for example with Activity Insights in AutoCAD. AI writes the description from the approved comments.
How much does such training cost?
At Syntalith from €1,150 net for a day's workshop for the team. Claude Team licences cost $20 a person a month. With 10 people and 1 hour a week, the payback is 0.9 months.
