Services

Six lines of production work

We take on problems where off-the-shelf products hit a ceiling and a thin AI wrapper does not work. We do not build brochure sites, landing pages or routine CRM customisation.

On this page

01 AI systems and LLM assistants ↓
02 Custom B2B platforms and portals ↓
03 Replacing SAP, Oracle and Salesforce ↓
04 Marketplace aggregators and e-commerce systems ↓
05 SaaS platforms and multi-tenant systems ↓
06 Custom analytics and BI ↓

AI systems and LLM assistants

Not a wrapper around a chatbot, but working AI systems: RAG over corporate data with source citations, local LLMs for compliance-sensitive work, assistants inside messengers and embedded in CRM. For sales teams, lawyers and support.

Qdrant vLLM Mistral Qwen bge embeddings

Why parsing is the real work

A good fit when

→ A complex product or a large knowledge base
→ Off-the-shelf AI add-ons did not stick with your staff
→ Compliance: the data must not leave your perimeter
→ It has to integrate with the CRM you already run

Custom B2B platforms and portals

Complex B2B systems with multi-role models, custom workflows and integrations. We build what off-the-shelf CRMs cannot hold, where customisation turns into a permanent tax.

FastAPI PostgreSQL React WebSocket Celery

Build or buy: the 30% rule

A good fit when

→ A partner network that needs its own portal
→ A workflow that does not fit a ready-made CRM
→ Several roles with different rights and different interfaces
→ A regulated industry — legaltech, medtech, fintech

Replacing SAP, Oracle and Salesforce

A full replacement of a foreign system — with data migration, processes preserved and on-premise deployment. Run process by process through a parallel track rather than as a single cutover.

FastAPI Accounting integrations RabbitMQ On-premise PostgreSQL

A good fit when

→ Regulatory or government requirements apply
→ The vendor left your market and you need a replacement
→ Integration with your accounting system is the key requirement
→ On-premise deployment is mandatory

Marketplace aggregators and e-commerce systems

Two-way synchronisation of stock and prices across platforms, automated repricing driven by margin rules, unit economics by SKU and channel, alerts on sales anomalies.

FastAPI Marketplace APIs ClickHouse Bots

A good fit when

→ The brand sells on three or more marketplaces
→ A catalogue of 200 SKUs or more
→ Oversells and penalties are a constant problem
→ You need one view of profitability

SaaS platforms and multi-tenant systems

Complete SaaS products with subscription billing, recurring payments, multi-tenant architecture and white-label capability. For companies that have outgrown a stack of no-code tools.

FastAPI PostgreSQL Billing PWA React

Multi-tenant: now or later

A good fit when

→ The business has hit the ceiling of a no-code setup
→ A subscription model with recurring payments
→ Several brands, schools or branches — so, multi-tenant
→ White-label for other companies is on the horizon

Custom analytics and BI

Not a BI tool with stock connectors, but analytics built around your processes. Real-time dashboards for management, demand forecasting with ML, unit economics by SKU, channel or cohort, exports for external reporting.

ClickHouse PostgreSQL Grafana ML pipelines

Measuring a channel nobody reports on

A good fit when

→ Standard BI tools do not cover your logic
→ You need real-time analytics, not yesterday's reports
→ Large data — tens of millions of rows, real load
→ ML models inside production analytics

Before you commit

What each of these costs, in writing.

Rather than a page per keyword, we publish the numbers and the failure modes. Every piece below answers a question clients ask before signing anything.

AI and LLM

Does ChatGPT send anyone to your site? Measure it in the access logs

Neither analytics nor Search Console answers whether AI bots visit you. Only your access logs do. Real numbers: 431 fetches by AI bots against 84 by Googlebot, and two traps that inflate the result sevenfold.

Integrations

What an accounting integration costs, and what the price actually depends on

What makes up the budget for integrating an accounting system with a website, CRM or marketplace: ranges for three typical scenarios, what quietly inflates a project, and why a fixed price without an audit is a bad sign.

AI and LLM

An AI assistant for your sales team: what to prepare before the project starts

What has to be in place before deploying an AI assistant: an audit of data sources, a master system per data type, access approvals and quality criteria. With a readiness checklist.

System replacement

How long a SAP migration takes in a large company, and what the timeline depends on

What determines the length of a SAP migration: the number of active modules, the volume of customisation, the integrations and the readiness of the client's team. Benchmarks by stage, a separate section on banks, and what stretches a project.

Marketplaces

Integrating with marketplace APIs: rate limits, errors and why stock figures diverge

Working with marketplace APIs in practice: per-method rate limits, asynchronous operations, idempotency, retries and priorities. Why stock figures diverge and how that gets fixed.

B2B platforms

Multi-tenant SaaS: design it now or retrofit it later

Three data isolation models for multi-tenant SaaS — database per tenant, shared database with tenant_id, schema per tenant. What a retrofit actually costs and when you do not need multi-tenancy at all.

FAQ

Before you write

What work do you turn down?

Brochure sites, landing pages and simple customisation of an off-the-shelf CRM. We take projects with complex logic, integrations, AI, data or compliance in them.

Can we start with an audit rather than development?

Yes. For complex projects we usually start with discovery: processes, risks and architecture first, and only then a fixed development scope.

Do you work on-premise?

Yes, and for sensitive data it is often the only option. We deploy on-premise, in your cloud, or on your own servers.

Not seeing your kind of work?

These six are the main ones, but we take adjacent problems where we have the expertise. Describe the problem and we will say honestly whether it is ours.

Discuss a project