Blog · Published · Updated
Company Brain for engineering design consultancies
Short answer
An AI knowledge base in an engineering design office finds the reasons behind past decisions, for example why an option was rejected on a similar project, with a link to the approved note and with access to the client's documents kept as it is. An AI application on company documents costs from €3,000 net at Syntalith. At 200 questions about past decisions a month and 20 minutes of searching each, it pays back in 1.5 months.
How we workDetails ↓
- 01Call30 minutes with an engineer, free
- 02PrototypeA working system on your process and data, free
- 03ImplementationTarget and fixed price in the contract; 50% at signing
- 04Acceptance50% once the agreed target is met
- net per application, fixed price before contract
- from €3,000
- from signing the contract to acceptance
- 4–10 weeks
- free prototype on your documents
- €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
Design office knowledge and AI: statistics 2026
1.5 mo.
payback of €3,000 at 200 questions about past decisions a month: €2,327 of work today, €352 with checking and the model. Scenario.
49%
According to Anthropic (2024), combining contextual embeddings with BM25 search cut failed retrievals by 49%, and by 67% with reranking.
48%
According to the European Commission (2026), 48% of small and medium-sized companies in the EU name a lack of expertise as a barrier to AI.
Source: European Commission, Flash Eurobarometer 578 (2026) ↗
37.9%
According to Eurostat (2025), 37.9% of EU companies in legal, accounting, consultancy, architecture and engineering activities used AI.
Source: Eurostat, AI by NACE activity (isoc_eb_ain2) (2025) ↗
11 of 13
According to the NoLiMa study (2025), at 32,000 tokens of context 11 of 13 models fall below half of the accuracy they reach with a short context.
Figures checked: 22 October 2026
Why did we drop this layout back then?
The office is working on the layout of plant rooms. A designer remembers a similar option from an earlier job, but not why it was rejected. The approved meeting note records the reason: the option required moving a room, and the client did not agree. Then starts the search through folders and for the person who was at the meeting.
The reason for the decision
useful
The condition that decided the choice, with the context of the job.
The drawing of the option
supporting
It shows the layout, but not why it was dropped.
The client's documents
restricted
Available only to the project team, also in the assistant's answers.
An option rejected in the past does not settle the result of a new analysis, and the assistant reconstructs the reasoning without deciding the current project. When a decision changes, the new finding is linked to the previous one, and the entry shows who wrote it and who can explain it.
What it costs and when it pays back
- Today
- 200 questions about past decisions × 20 min = 66.7 h (€2,327)
- With the system, a person checks the result in 15% of the time
- €349
- Model, 1 call per case, Claude Sonnet 5.5
- €3
- Cost of one case
- €11.63 today, €1.76 with the system
- Saving
- €1,975 a month
Payback of €3,000
1.5 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: 6,000 input tokens and 500 output tokens per call at Anthropic's rates, at the ECB rate of 1.1205 USD per euro on 22 October 2026.
The model is a small item here. The result depends on the time that searching and asking around take today, and on how much of it remains for checking the answer.
Before we price the build, we run a test on 20 to 100 questions the team has already asked: we compare the application's answer with what the employee found by hand, and we count the time from the question to the source. The test takes 5 working days and costs €0.
When search in your current system is enough
If designers know the project and the document name, the tool they already work in is enough. The BIM 360 Document Management documentation describes searching by names and attributes, and filters for versions and review status. An assistant makes sense when people remember what the problem was about but not which project discussed it, or when they have to link a note with later agreements.
A known project and document name
search in the current system
no application
Notes without a description of the decision
a library of reasons with descriptions
tidying up
Questions about a problem across many projects
an assistant on approved notes
from €3,000
Where to start
The first scope is one library of approved notes and lessons from finished projects. Designers bring questions that recently meant tracking down someone from the meeting. Industrial quoting is covered in the post on a knowledge base for quoting.
For the first call, one question that keeps coming back to colleagues and where the team looks for the answer are enough. You do not need to send confidential documents, and you receive the written plan within 2 working days.
Worked example · Scenario
How we count the payback: answers from company documents
We run the same count for your documents in the free review.
€3,723
a month for finding answers to 800 questions in documents
Payback: 1 mo.
Our assumptions are 8 minutes to find an answer in documents or ask a colleague, and checking in 15% of the old time. €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: Claude Sonnet 5.5, about 6,000 + 500 tokens per answer from documents, at the ECB rate of 1.1205 USD per euro on 22 October 2026.
See the full calculation →
