Schedule, budget from the bill of quantities, site progress and variations in one place. The site manager enters data from a phone, the office sees the cost overrun the same week.
The schedule gets updated once a month before the site meeting. Someone else keeps the budget in a separate file. Ask how much is left for the structural shell and you get three different numbers.
The subcontractor does extra work because the site manager asked verbally. The variation order is written up after the fact, and the client learns the cost from the invoice and refuses to pay.
Site photos sit in the manager's messaging app, diary entries in a binder in the site office, meeting notes in an email. Two years later, at a warranty claim, nobody can find when the slab got flooded.
Built around your sites, your site managers and the files you work in today. We agree the scope and rollout order together.
Three years ago features like these needed a data science team. Today language models read emails, documents and photos, and we build them into the system we make for you. Below is what makes sense in this solution. A person approves, AI prepares.
AI reads the estimate as a PDF or a Norma export, recognizes sections, items, quantities and prices, and builds a stage budget for the estimator to approve.
Example a 340-item tender estimate in PDF → a stage budget with items pinned to schedule tasks
A phone photo gets a stage, a location and a proposed diary entry. The site manager corrects one word instead of writing a paragraph.
Example a photo of slab reinforcement → entry "ground-floor slab reinforcement, grid A–D, ready for inspection" with a date and schedule item
The model compares the pace of work with the plan and with previous sites. When a stage will not close on time, it says so before you see it in the schedule.
Example plastering slower than planned for the third week running → an alert with a delay forecast and the impact on flooring
Instead of digging through spreadsheets, you ask in plain language. The answer comes from system data.
Example "how many variations are waiting for client approval at Wilanów?" → a list of four with amounts and submission dates
We import the schedule from MS Project and the estimate from Norma rather than re-keying them. Invoices and costs go to your ERP, entries to the EDB if you keep an electronic site diary.
We start with one site that is about to begin or is halfway through. The site manager works in the system alongside the spreadsheet until the spreadsheet is no longer needed.
You have the diagnosis, we build the solution. Web applications, B2B portals and automations for companies without a large IT department. Today a system can read emails and documents, suggest decisions and answer customers on its own, so we build that in from the first version, not as an add-on a year later.
We agree scope, price and dates upfront, show progress every week, and the code and data stay yours.
You describe how the site meeting runs today and where its numbers come from, we tell you what can be done and how long it takes.
Write to us