Cologne · document intake for small businesses

Sorting mail, typing up receipts, hunting for PDFs? That can run automatically.

I set up a digital document intake for you: invoices from e-mail and scans are read, filed and handed over to DATEV, lexoffice or sevDesk. From €2,900 net one-off plus €129 a month — you pay 50 % only after acceptance.

Free first call See prices

Servers in GermanyFixed price up frontData export any time

Fig. 0 — System sketch, schematic

Standard solutions

Solutions

A standard solution, not a custom project: one document stream, proven open-source building blocks, no licence fees. Price and acceptance criteria are fixed up front.

LSG-01

Digital Document Intake — pilot in 2–3 weeks

Mail · e-mail · scan · e-invoice

Fig. 1 — Schematic view

Mail, e-mail, scans and faxes land on the desk every day — and get sorted by hand. A digital intake workflow bundles all channels, automatically reads sender, date, amounts and document type, and files every document sorted and full-text searchable. Anything unclear lands on a review list instead of in the wrong folder.

Fixed price from €2,900 net

Services

Not every process needs AI. I automate with fixed rules first — AI only comes in where fixed rules are no longer enough.

Automate processes — without AI

File e-mail attachments and scans automatically
Enter data once instead of typing it twice
Hand invoices over to DATEV, lexoffice or sevDesk
Send reminders and monthly overviews automatically

AI — only where it pays off

Read documents: sender, date, amounts, document type
Unclear items go to the review list, not the wrong folder
Pre-sort and assign e-mail inquiries
On request entirely without cloud AI, e.g. for tax firms

Case studies

Selected Projects

Real projects, described anonymized — technology, structure and tooling only. Two examples following the same pattern: problem, architecture, result.

REF-01

Directory platform with a data pipeline from official registries — own product, live

Django · PostgreSQL · HTMX · SEO

Fig. 2 — Schematic view

Problem: The official registry data of a regulated profession is scattered across dozens of registry bodies — HTML lists and PDF registers, with no central search.
Architecture: Server-rendered Django with HTMX and Tailwind on PostgreSQL. Idempotent scrapers load the registries (HTML and PDF) into a three-stage pipeline — raw, staging, production — with manual approval gates between stages. SEO landing pages per category, location and combination; redirect middleware (301/410) keeps the URL structure clean; contact requests flow via n8n into an ops backend (Fig. 2).
Result: A live directory with around 870 profiles from official sources; the index grows in a controlled way, registry by registry. ~870 profiles from official sources

REF-02

Agent workflow: from photo to marketplace listing — internal tool

LLM · Vision · APIs

Fig. 3 — Schematic view

Problem: Creating a listing on a major online marketplace takes many manual steps: prepare photos, research category and required attributes, write copy, publish.
Architecture: Agent-driven workflow: script-based image prep (background removal, normalizing), a vision model reads the photos and grounds the listing copy in what is actually visible, category and attribute schemas come live from the marketplace API — nothing is published without explicit approval (Fig. 3).
Result: Photos plus a short note become a reviewable listing draft; only approved content gets published — no invented product claims. publishing only after approval

See all projects →

Person & approach

About me

I'm Igor Stolyarevskiy, an IT consultant from Cologne — with a master's degree in IT and more than ten years of professional experience. I help small businesses get paperwork and retyping out of the office: from the first conversation through setup to day-to-day operation. I know the starting point from my own experience as an entrepreneur: full inboxes, processes that grew over time, and the question of what is really worth it.

With me you have one contact from start to finish: I do the process check, set up the solution and look after it myself afterwards. I use proven open-source building blocks without licence fees; your data sits on servers in Germany and can be exported at any time. And if automation doesn't pay off for you — rule of thumb: fewer than about 15 documents a day — I'll tell you so plainly.

Inquiry

Contact

Quick inquiry: two minutes, three questions. Or give me a call — the first call (30 min.) is free, by phone or at your office.

Prefer to talk? +49 221 560 75 100

iks.reachout@gmail.com

Send a quick inquiry

Reply usually within one business day