← insights

AI implementation · 05.2026

A company health report in seconds.

Profile checking company creditworthiness
Process company health report
Scope 3 bots + a language model

From a tax ID to a finished report

Registry.io VAT whitelist Beneficial owners Related entities Registry filings
01 Aggregation tax ID check, parallel queries, 24 h cache
02 Financial analysis ratios, charts, PDF
03 Gemini model health assessment, risks, conclusions
04 Report live status

Starting point

The data is public, but scattered across many sources.

Registries, the VAT whitelist, beneficial owners, related entities, financial statements as PDFs from the registry. Every source had to be opened separately. A few hours of analyst work for one report, and the quality depended on who wrote it.

What we built

Three bots and one model.

The first bot checks the tax ID and queries every source at once, then assembles the answers into one whole — with the option to re-run at any time to check whether the data has changed. The second reads financial statements, calculates profitability, liquidity and debt ratios, and draws charts into a PDF.

The third hands the collected data and documents to an LLM. The model writes the financial health assessment, a description of the ownership structure, a list of risks, and conclusions. The report is generated in the background, and the user gets the complete result.

In the end

The model gets the data, it doesn't look for it.

The model has a narrow task and works only on documents for the given company. It doesn't search for data itself — the bots hand it over. That means the report can be shown to a client without checking every sentence, guarding against AI hallucinations.

Results

4–6 h → 10–30 min report preparation time
2–3 h → seconds data collection
3–5 → 10+ data sources
24/7 report availability
Tools Google Vertex AI — Gemini Registry.io API VAT whitelist (Ministry of Finance) National Court Register / business registry SignalR PDF and chart generation

A report that used to take half a day.

We don't name the company. Numbers come from the audit and process measurement at the client.

Take the Chaos Scan Let's talk
← all insights next Recurring content with Lumina →