AI & agentic automation
Agentic AI for business processes. Emails, invoices, document extraction — routine gone. AI wired into your existing systems, not yet another isolated chatbot.
Learn more → PLATE 01 / HOME SOLUTIONBOX · SOFTWARE STUDIO · v1.0
// SOFTWARE STUDIO · CZ
Software that companies
actually need.
AI integration and system modernization. For companies that can't afford to wait. We wire AI into what you already have — fit to your needs. Working systems, not slideware.
AI picked to fit AI agents in your app Faster shipping Compliance & audit log
// OUTCOMES, NOT LINES OF CODE
40×
faster operations — contracts from 2 h to 3 min
days → 4 h
a pipeline that ran for days now finishes in hours
4 mo.
from zero to a live taxi platform with ~50 cars
40,000+
invoices filed through KSeF in 3 months
// WE BUILT FOR
ČSOBVendavoAtlas CopcoZásilkovnaContineroMěsto ZlínCarivioTrafinOilMyJourney
// SCROLL TO EXPLORE 01 / 06
02 · CAPABILITIES
What we're good at.
Three things we do every day — and we do them properly.
Is your own system slowing you down?
We found a bottleneck in a bank where contract generation took 2 hours. After our optimization — 3 minutes. This is what we do — we find what's broken and fix it.
Learn more →Development from scratch, or where you left off
We delivered the complete Carivio taxi app in 4 months. Backend, mobile apps, AI pricing, real-time tracking. When it needs to work, we take care of everything.
Learn more →Robust KSeF / e-invoicing integration
Most KSeF integrations are fire-and-forget — and when the state system goes down, invoices vanish. We build it durable: idempotent submission, retry, reconciliation, audit log. No lost invoices, no penalties.
Learn more →// HONEST REVIEW
Why hire a studio when
AI writes your code?
An honest answer from people who use these AI tools every day.
AI writes a prototype, not production
Cursor or Claude Code can ship a demo in an hour. Production is another league — security, edge cases, scale, compliance, audit log. Without senior review it collapses the first quarter it runs in a bank.
Integrations don't grow on their own
ChatGPT won't write a KSeF client for Czech invoicing. It won't wire you into Pohoda, the legacy SAP, or your ERP. That is weeks of debug, spec know-how, and vendor coordination — not a prompt.
Compliance and audit log
GDPR, SOC2, internal security policy — AI-generated code routinely ships through third parties. For a bank, city or factory that means legal risk. We handle it: local models, decision audits, data residency, DPO-friendly architecture.
Ownership and upkeep next year
Who fixes it when it falls over in six months? Who knows why it is written this way? AI generates docs, but we defend them in front of your CTO and auditor. No lock-in — we hand over the keys and a runbook.
// DISCLOSURE
We don't hide the AI. We use Claude Code, Cursor and Codex every day — that's how we ship in weeks, not months. The difference is the senior review that sits between the AI and your production.
// WHY SOLUTIONBOX
Model-agnostic.
Compliance-ready.
Ship-friday.
Four things we do differently than most studios.
01 // MODEL-AGNOSTIC AI
AI that does the real work
We pick the model to fit the need — Claude, GPT, open-source, local Llama for sensitive data. No vendor lock-in, no generic wrappers. Agents that read documents, call tools, and escalate only edge cases.
02 // SHIP FAST
Faster shipping
Months last year, weeks this year. AI coding assistants, agentic pipelines, reusable components. Fewer meetings, more code in production — and senior review on every commit.
03 // AGENTS IN-APP
AI agents in your app
Have a working app? We add AI agents to what already runs — no rewrite, no lock-in. Wired into your APIs, auth, and data. Weeks, not quarters.
04 // COMPLIANCE
Compliance & audit log
GDPR, enterprise-grade audit log for every AI decision. We know why, what, when. For banks, public sector, and manufacturing — where you must prove AI did the right thing.
03 · OUTCOMES
The only slide
that matters.
Numbers. Not adjectives.
2 h → 3 min
contract generation, minutes not hours (ČSOB)
days → 4 h
a data pipeline that used to run for days (Atlas Copco)
~90 %
of citizen questions answered correctly (Zlín)
20 h → 30 min
nightly data processing, every day (TrafinOil)
04 · SELECTED WORK
Selected work.
Real problems, real solutions.
ČSOB 40× faster
Contract generation 40× faster
Generating client contracts took over two hours. The system crawled through millions of records with inefficient queries…
.NETC#SQL Server
Full reference →Continero
One API for all your AI
The client wanted to use AI across the business — image and video generation for marketing, text AI for automation — but…
OpenAIAzure AIDALL-E
Full reference →Město Zlín ~90% AI accuracy
AI Chatbot for a city
The city office was buried in repetitive citizen questions — opening hours, fees, waste, events — and foreigners could n…
OpenAILangChainPython
Full reference →05 · TEAM
Who's behind it.
No management overhead. You talk to a developer, not an account manager.
Bc. Miroslav Lalík
Founder & Tech Lead · AI Solution ArchitectApplied AI architect and senior .NET engineer, 10 years in. Builds production RAG and agentic systems wired into real .NET backends — from KSeF to a municipal chatbot at ~90% accuracy. Previously ČSOB, Vendavo, Atlas Copco.
.NETC#RAGAI agentsPythonAzureSQL
Tomasz Krawacki
Fullstack DeveloperFullstack developer focused on mobile apps (Flutter, React Native) and modern frontend (Next.js, React).
FlutterKotlinSwiftReactNext.jsTypeScript
Radek Janulek
Cloud DevOps LeadEight years in cloud infrastructure and DevOps. RPA, enterprise automation and monitoring at Tieto. Owns the infrastructure layer across projects — CI/CD, infra-as-code, observability, incident response.
AzureDevOpsCI/CDRPAMonitoringDockerIaC
LinkedInIng. Mario Nitzke
Fullstack EngineerMaster of Engineering (Ing.). Worked on the Carivio platform, plus wellyou.cz and cervenesolarium.cz — backend API design and frontend integration end-to-end.
.NETC#TypeScriptReactNode.jsSQLAPI
LinkedInBc. Michal Havlík
Data SpecialistData specialist — Kafka and Snowflake. Data engineering at Česká spořitelna, where data reliability and scale are real constraints. Pipelines that don't drop records; schemas that survive change.
SnowflakeKafkaSQLPythonETLData Eng
LinkedInBc. Martin Matis
Database & DevOps EngineerFive years of DevOps in the armed forces, fullstack at myJourney, now an SQL and database specialist. Operational discipline plus database depth — data integrity, schema governance, ops-heavy workloads.
SQLDatabasesDevOpsCI/CDLinuxOps
Lukáš Vostrý
QA → Frontend EngineerStarted in QA, moved into frontend — and it shows: UI that's tested, not just built. Worked on solutionbox.cz and a pizzeria SaaS.
QATestingFrontendTypeScriptPlaywrightUI
// FAQ
PLATE 06 / CONTACT LET'S WIRE SOMETHING UP
06 · CONTACT
Got a project?
Get in touch.
No non-committal 90-minute pitches. Describe what you're solving — we'll reply within 24 hours.
SOLUTIONBOX · STONAVA · 2026 END OF HOME