Construction estimates with stated quantity assumptions
The system lines up the items to price and marks which quantity is confirmed and which is provisional. The estimator approves the basis of each price.
Automation, paid once
from €3,000 net
Test on your process: €0
You pay 50% after acceptance
How much does automating construction estimates cost, and when does it pay back?
Short answer
Automating construction estimates costs from €3,000 net. In our scenario it pays back in 1.7 months. Today, preparing 30 estimates by hand costs €2,094 a month. With the system, the same work costs €315. The estimator approves the basis of each price. The system shows which quantity is certain. It does not do the take-off from drawings. The test on your process is free.
Statistics
Quotes and AI: statistics 2026
−95%
According to Anthropic (2025), compiling information from reports takes an estimated 95% less time with AI.
According to the European Commission (2026), 42% of EU small and mid-sized companies already use AI or automated management systems, mostly in a limited way.
We count the payback from the time saved. The process also brings extra margin from sales: about €1,033 a month in this scenario (the assumptions are under “How we calculate it”). According to Harvard Business Review (2011), in a study of 1.25 million sales leads, firms that tried to contact a lead within an hour were nearly 7 times more likely to reach a decision-maker than firms that tried an hour later.
30 × 120 min = 60 h × €34.90 = €2,094 a month. With the system, a person checks the output in 15% of the old time (€314) and the model costs €0.69. That leaves €315. The saving is €1,779 a month, so €3,000 pays back in 1.7 months. The payback counts the time saved only. On top of it comes extra margin from sales: about €1,033 a month in this scenario.
Assumptions: 120 minutes to price the works 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: Claude Sonnet 5.5, about 4,000 + 1,500 tokens per draft quote, at the ECB rate of 1.1205 USD per euro on 22 October 2026. The extra margin is a scenario: we assume that 1 in 100 estimates sent 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.
The client sends the bill of quantities and drawings
Client
The estimator retypes the items
Team
Estimates some of the quantities
Team
The total looks precise
Team
The difference shows up on site
Team
With the system
The documents arrive in the inbox
Client
Lines up the items to price
AI
Marks provisional quantities and gaps
AI
The estimator approves the basis
Person
An estimate with stated assumptions
System
What stays with people: The estimator approves the basis of each price. The system shows which quantity is certain. It does not do the take-off from drawings.
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%
the system sends the answers itself, without human typing
time from the arrival of the e-mail to the ready response (median)
30 s
time from the arrival of the e-mail to the ready response (median)
e-mails that require a response receive a ready-made draft
100%
e-mails that require a response receive a ready-made draft
less work for every 1000 answers (estimate)
47 h
less work for every 1000 answers (estimate)
Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.
It splits an enquiry into line items and looks for the basis of each price in past quotes and approved rules. A line with no basis stays unpriced and goes to the right person with a specific question. Reading one enquiry costs about €0.0008 of model work.
“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.”
You choose the test cases. We anonymise them on request.
They stay in the EU and we delete them after the test.
We sign the NDA and the data processing agreement before we receive anything.
After acceptance you keep the code, the test set and the documentation. You pay for licences and model usage directly to the provider.
Questions
How much does estimate automation for a construction firm cost?
From €3,000 net, paid once. After the 5-day test the build takes 2 to 6 weeks. You get a fixed price before the contract: 50% on signing and 50% after acceptance on your own estimates.
Does the system do the take-off from drawings?
Not in the first scope. The take-off and the technical assessment stay with the estimator. The system makes sure a provisional quantity does not look certain.
When does it not pay off?
Below 5 estimates a month the payback takes more than a year. Then it is better to start with ChatGPT or Claude for the team, from €1,150 net.
Would estimating software be enough?
Estimating software calculates from ready items. The system helps earlier, when the bill of quantities arrives in different forms and the items have to be lined up and checked.
What do we need to prepare?
10 to 50 estimates from recent months with their bills of quantities and final accounts, and your base of unit prices.
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.
Claude 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.
customer service
