6
Dutch data sources, in the dossier
Novilla · Пример из практики
Универсальная платформа для оценщиков недвижимости в Нидерландах, которая автоматизирует весь рабочий процесс оценки — от приема заказа до составления итогового отчета.

Novilla объединяет все инструменты, необходимые оценщику, в едином рабочем пространстве. Заказы, документы, оценки и переписка с клиентами хранятся в одном месте, а не разбросаны по разным почтовым ящикам и таблицам.
ИИ-агент берет на себя рутинную работу (чтение писем, сбор данных из различных источников, заполнение полей и формирование отчетов в формате PDF), благодаря чему оценщики могут сосредоточиться на тех суждениях, которые действительно имеют значение.
One rule runs through all of it: the AI drafts, the appraiser decides. It can write a reply, but it cannot send one. It can never mark an invoice or a payment as done.

Краткое руководство по работе в Novilla — от приема заявки до подписания отчета.
Dutch data sources, in the dossier
A dossier and a Dutch reply per email
The AI writes, the appraiser sends
Her own workbook, to the euro
PDF reports, rendered from the dossier
Рабочий процесс был раздроблен между электронной почтой, файлами PDF, таблицами и полудюжиной порталов данных. Каждая оценка сопровождалась одним и тем же циклом «копировать-вставить», а время неумолимо шло.
Время, потраченное на ввод данных до начала фактической оценки.
Данные о недвижимости хранились на порталах, которые никогда не взаимодействовали друг с другом.
Письма от клиентов и брокеров заглушили сигнал шумом.
Сборка PDF-файлов была медленной, ненадёжной и чреватой ошибками.
First, we watched the work.
Before writing any code, we extracted, translated and analysed eight YouTube tutorials of the appraiser's own process.
They showed eight workflow steps, full of manual data entry.
Novilla was designed from that map.
Единая интеллектуальная рабочая среда, обеспечивающая полный цикл проведения оценки (прием заявки, исследование, переписка и сдача результатов) с помощью ИИ-агента, работающего в тандеме с оценщиком.
A dossier's status is split into six tracks: report, delivery, billing, archive, review and QA. One status column cannot say “delivered, but not yet paid”. Six tracks can.
A dossier only enters Novilla when it is explicitly picked up. From there, the work is shared between the parts below.
Заказы, документы и оценки — всё в одном рабочем процессе.
Самостоятельно выполняет задачи, позволяя вам сосредоточиться на принятии решений.
Читает, готовит и архивирует важную корреспонденцию.
Извлекает нужные записи из каждого источника.
Предоставляет отполированные PDF-файлы без лишних хлопот.
Real screens from the working product. Client names, addresses and contact details are blurred.
The board runs through eleven stages, from request and terms to delivery, payment and closed. Each card says what the dossier is waiting for, such as the client's akkoord or an inspection to book, and how many drafts need approval. Filters pull out the dossiers with a draft waiting or a deadline passed. If a dossier is pinned to a stage by hand, the card still says where the facts put it.

Open a dossier and its status reads as separate tracks: report, delivery, billing, archive, review and QA, next to the dossier's state in NWWI and Provadie. Below it, the stage map shows how far the dossier has come. A stage that still needs attention, such as an akkoord that has arrived but is not signed off, is flagged instead of skipped.

Every outgoing message waits in the dossier's draft list as needs approval. The appraiser opens it in a full editor, can switch the template or attach the PDF report, and only then presses Approve & send. Nothing leaves on its own.

Asked for comparables, the agent inspects the dossier, reads its data, gathers candidates and compares them, and reports each step as it completes. The answer is a table: sale date and price, living area and plot, distance, the indexed price and the adjusted value for every reference it kept, with a range and a confidence score on top. It also lists what still needs checking.

When the agent fills part of the Provadie report, the fields open in a pane beside the conversation. Each field shows where its value came from: Provadie, Novilla's own record, or the agent. Fields the agent filled are marked for review, and a block can be filled again or handed to the agent in one click.

Novilla keeps the facts of a dossier from each source next to each other: Provadie, NWWI, Brainbay and its own record. When two sources disagree, the field is flagged, and the appraiser compares the values and picks the one that counts. Once the report is signed, the subject facts and comparables lock.

Invoices and payments bound for Snelstart queue up as pending writes. The appraiser can open the exact payload first, and only approved writes are booked. Shown here on the development adapters.

Once a quarter, the appraiser sets the quarter labels and pastes the new NVM summary. The structure and wording of the section stay fixed in code so the figures stay exact, and the agent fills the numbers from the NVM Kwartaalcijfers PDF.

Brainbay holds the comparables an appraiser needs, but it offers no API. So a Playwright bot-worker drives it through a browser, with its jobs queued in BullMQ on Redis. Funda listings arrive through Apify.
Mail arrives through a Microsoft Graph webhook. A language model proposes the dossier, the intent and a reply in Dutch, and then it stops. The appraiser approves every send. The AI can never mark a billing or payment step complete, and never touches payment links or invoice numbers. Every sent message is kept as a snapshot that cannot change, and idempotency keys stop a retry from sending twice.
Provadie is the appraiser's report platform, so Novilla works beside it. We reverse-engineered the form language behind its screens. An extractor turns that language into a 4.8 MB generated catalog, and an interpreter draws our own report pane from it. A parity harness compares the pane with Provadie: page by page offline, and live but read-only across about 20 sections. Every gap is ranked by its cause, not by where it shows up.
An extractor can lose meaning without throwing a single error. So a conformance audit reads Provadie's form language a second time, sharing no code with the extractor. Where the two readers disagree, something was lost. A reveal probe then answers every conditional question by itself, to prove that all 687 conditional rows can appear. It takes about 9 seconds.
We built the onderbouwing module from the appraiser's real, completed workbook. It showed rules a blank template hides: her typed overrides beat formulas, Excel's AVERAGE skips empty cells, and multipliers change per dossier. One row, the energy label, cannot be decoded from the file at all, so the module flags it instead of guessing. Where the module helps, it offers evidence, never amounts. Kitchen, bathroom and boiler come from her inspection, so there it stays silent.
Market analysis started from the appraiser's own ChatGPT prompt, which became the spec. The figures never pass through a model. Fixed parsers read NVM quarterly figures and Funda demand scans and reproduce her reference output line for line. Live connectors now fetch both: the NVM figures by download, and Funda's demand figures from the chart data on its result page.
Business results, like time saved, are not in yet, so they are not on this page. These are engineering checks. Each one compares Novilla's output with something the appraiser made by hand, or with Provadie itself.
Reproduced to the euro, overrides and all
Audit findings from an independent second reader
Parity findings, narrowed to gaps ranked by cause
Form rows revealed in about 9 seconds
NVM quarterly cells, matched one for one
Funda demand values, matching her report
Every appraisal in one dossier
The AI drafts. The appraiser sends.
Our pane, checked against Provadie's own screen.
Узнайте, как мы можем оптимизировать ваш рабочий процесс.