Website in the browser
Turnkey houses
A house customer wants the order of price before a call, and later wants to see what the build is waiting on. Here the range is calculated at once, a phrase about family, sotkas, budget and winter becomes a configuration with an explanation, and in the account the roof is already going up — the boiler is not chosen.
Scenario: Yarus from Krasnodar — fictional: twelve finished turnkey projects, four materials. Packages from a warm shell to finishes stay in the estimate.

What the demo shows
How to try it
Read a phrase
Open Estimate and press “Example”, or paste “family of four, an 8-sotka plot, budget 9 million, we live there in winter”. Under the field you’ll see what was understood.
Move the slider
Set 200 m² and one storey on 4 sotkas. The plot sketch says the house takes too much of the land.
Open a project
On Beryozovy the range matches the calculator. “Open in the estimate” carries the same parameters.
Choose a boiler
In the account the roof is marked as the current stage. Choose gas or electric and send the decision — the request appears in the owner dashboard.
No paid neural networks
There are no paid neural network requests: the phrase is parsed by rules in the browser — family, metres, sotkas, millions, material, storeys, package and soil. In a production version a language model understands the text, with the company’s norms and the soil survey given to it as tools — it won’t quote a price outside the estimate. The range is a plausible model, not a contractor’s price list. The company, the projects and Marina’s build are fictional.
The demo runs without OpenAI, YandexGPT or GigaChat API keys. Wherever a production system calls a model, there’s a local stub with the same interface — so the demo is free, always available and never makes things up.
What a production project adds
- Norms and rates from an estimating program or 1C; the survey and the siting from the design
- The build calendar from the schedule of works, stage photos from the site manager’s report
- Request parsing by a language model (YandexGPT or GigaChat) with the norms and the plot as tools; the request goes to a CRM
- The owner’s decisions as a contract addendum, with a notice to the site manager in Telegram or MAX
Stack
- All demos by stack:
- Next.js
- React
- TypeScript
- Next.js 16
- React 19
- TypeScript
- Tailwind CSS 4
- Server Actions
Want the same for your business?
Tell me about your task — I’ll tell you what from the demo fits, how long it will take and what I’ll need from you.
More for this task
The whole section- live
Next.js website · service landing page
Dental clinic landing page
A one-page clinic website that brings in patients: a quiz suggests a treatment, a calculator prices the plan with installments, online booking shows doctors’ free time, and an AI consultant answers from the price list. The headline is A/B-tested; leads and goals are visible in the owner dashboard.
- Next.js
- React
- TypeScript
- live
Next.js website · B2B, multi-page
Manufacturing company website
A multi-page website for a steel structures plant that sells on its own: a calculator prices a building with a live drawing, a builder assembles a technical specification, case studies filter by industry, you can apply for a job with a CV, and site search understands queries in plain words.
- Next.js
- React
- TypeScript
- live
Next.js website · catalog, map, comparison
Real estate catalog with smart search
A real estate agency’s apartment catalog: type “two-bedroom near the metro under 12 million” and the search sets the filters itself, shows apartments on a city map, compares up to four and sends new ones to Telegram.
- Next.js
- React
- TypeScript
