Projects

Selected projects from recent years, three different industries, one principle: I build automation as infrastructure, not marketing slides. Numbers shown are illustrative; they convey scale and impact, not exact operational statistics.

Real projects & websites

Receipt Maker app preview
Own tool · free

Receipt Maker

Receipt and invoice generator running entirely in the browser, nothing is uploaded. Thermal 58 and 80 mm rolls, A4, per line VAT with a summary, Code 128 and EAN-13 barcodes, payment QR codes. Hand written QR and Reed-Solomon encoders, zero dependencies, 196 tests.

Vanilla JSVATBarcodes
Optik Dvořák website preview
Client website

Optik Dvořák

Website for a family-run optician in Pilsen, eye exams, designer frames, offers and contact.

TypeScriptVite
Richard Topinka website preview
🔒 Client website

Richard Topinka

Portfolio for a fine-art and portrait photographer from Pilsen. Themed galleries with a focus on atmosphere.

HTML/CSSGallery
Autoservis Topinka website preview
🔒 Client website

Autoservis Topinka

Website for a car repair shop in Pilsen, services, inspections, pricing, booking and contact.

WebBooking
Lynx Studio website preview
Side project

Lynx Studio

Creative studio for startups and brands, digital experiences that connect and perform.

Studio
Synthetix website preview
Side project

Synthetix

Landing page for AI automation and integrations, from hero to call to action.

AI agency
East Hills Barbers website preview
Client site · Australia

East Hills Barbers

Website for a barbershop in Sydney (East Hills, NSW). Premium dark look, services and pricing, plus online booking through Cal.com, walk in or book in a couple of taps.

WebOnline booking
The Meat Boss Butchery website preview
Concept · Australia

The Meat Boss Butchery

Concept website for a family butcher in Padstow (NSW, Sydney). Order your cuts from your phone, say how you want them trimmed, pick them up at the counter without queueing. Built on spec as a demonstration, the shop is not a client.

WebOrder ahead
Nexora website preview
Side project

Nexora

Product website for an AI agent, from hero to pricing.

SaaS / AI
Vrstva website preview
Side project

Vrstva

Studio for tech brands, strategy, design and development on one site.

Creative studio
Synapse website preview
Side project

Synapse

Studio for UI/UX, branding, illustration and web, a portfolio presentation.

Design & portfolio
Fencl Video app preview
🔒 Client demo

Fencl Video

A clickable prototype of an AI tool for scoring marketing videos, verdict, weak-spot heatmap and top 3 fixes within two minutes.

Next.jsAI product
Ippa Café pitch preview
🔒 Pitch · password

Ippa Caffe pitch

A pitch website for the Ippa café in three languages (CZ / EN / DE). Client demo, password protected.

Pitchi18n
···
In progress

Synx

A side project in development. Details coming soon.

In development
Sample case studies
Illustrative model, not a delivered engagement Logistics Data pipelines Scope: ~6 weeks

Invoicing automation

A global logistics company processed international invoicing by hand: a team of four re-typed data between the TMS, the customs database and accounting. Every shipment waited on paperwork, 48 hours on average.

Starting point

  • 4 full-time employees just re-typing data between three systems
  • ~3% manual re-typing error rate, every error meant a customs delay
  • Invoicing capped growth: more shipments = more people

Solution

I built event-driven orchestration on custom middleware: every event in the TMS (loading, border crossing, delivery) automatically triggers data validation, customs document generation and posting to accounting. It connects to the existing systems via API, so the company didn't have to change software. People handle only the exceptions the pipeline flags for manual review.

  • Connected to the existing TMS and accounting system via API, no software replacement
  • A validation layer with rules for 14 countries
  • An exceptions dashboard, the team sees only cases that need a decision

Solution preview

#SH-88214Prague → HamburgProcessed · 9 min
#SH-88215Brno → ViennaProcessed · 12 min
#SH-88216Ostrava → KatowiceIn progress · validation
#SH-88217Prague → RotterdamException → manual review
Today: 0 shipments⌀ processing: 11 min● pipeline running

Pipeline monitoring dashboard preview (illustrative data).

Result

48 h → 11 minshipment processing time
−97%documentation error rate
3.2 monthsreturn on investment

The figures above are modelled, not measured at a client. They show the scale and type of impact, not the operating statistics of a delivered engagement. Documented figures appear only in the Galochrom study above.

Illustrative model, not a delivered engagement Banking AI agent Scope: ~8 weeks

Internal AI assistant

A bank's internal helpdesk received over 900 queries a day, from password resets to interpreting internal policies. Twelve operators dug through thousands of pages of documentation for answers. Public AI tools were unusable due to regulation.

Starting point

  • Average response time of 4.5 hours, with daytime peaks
  • Strict requirements: no data may leave the bank's infrastructure
  • Knowledge scattered across directives, wikis and e-mail threads

Solution

I deployed a stateful conversational agent on RAG architecture, running entirely in the bank's private cloud. It was trained exclusively on internal documentation; it backs answers with source citations and hands complex cases to humans with the full conversation context.

  • A private vector database, APIs with no data retention
  • Every answer linked to its source directive, auditability
  • Escalation protocol: uncertainty → handover to an operator, never a guess

Solution preview

What's the limit for instant payments on business accounts?
The instant payment limit for business accounts is CZK 2,500,000 per transaction. Payments above this limit automatically fall back to standard processing.Source: Directive PL-2024/07 · art. 4 par. 2
And who can raise the limit for a client?
Limit increases are approved by the risk department at the request of the client's banker. The request form is in the system under RM-07. Shall I hand this over to an operator?Source: Directive RM-2023/11 · art. 7
⌀ response: 40 s78% without escalation● data never leaves the bank

Internal agent conversation preview (illustrative data).

Result

78%of queries resolved without an operator
4.5 h → 40 smedian response time
0data leak incidents

The figures above are modelled, not measured at a client. They show the scale and type of impact, not the operating statistics of a delivered engagement. Documented figures appear only in the Galochrom study above.

Illustrative model, not a delivered engagement SaaS Predictive middleware Scope: ~5 weeks

Customer churn prediction

A fleet-management SaaS platform was losing customers quietly: when a client stopped using the product, the team found out only from the cancellation notice. Customer success reacted late and indiscriminately.

Starting point

  • Monthly churn of 4.1%, growing with the customer base
  • Churn signals sat in telemetry nobody evaluated
  • Customer success called customers blindly

Solution

I designed predictive middleware that reads product telemetry in real time, scores each account's churn risk and triggers graduated interventions on its own: from a personalized onboarding e-mail to a task for the account manager with a precise description of what's happening with the client.

  • Connected to product telemetry, CRM and e-mailing via API
  • A risk model retrained weekly on fresh data
  • Interventions escalate by score, automation handles light cases, people the critical ones

Solution preview

Fleetio Trans 18 stable, no action
Logimax s.r.o. 54 → onboarding e-mail sent
TransCargo CZ 87 → task for the account manager
Detection lead time: 0 daysMonitored: 0 accounts● model retrained 2 days ago

Churn risk dashboard preview (illustrative data).

Result

−31%customer churn per quarter
9 daysaverage risk detection lead time
higher retention campaign reach

The figures above are modelled, not measured at a client. They show the scale and type of impact, not the operating statistics of a delivered engagement. Documented figures appear only in the Galochrom study above.

Dealing with something similar? Write to me, I'll gladly look at your case and tell you whether and how it can be automated.

Get in touch

Got an idea or a project? Reach out, I reply fast.

Write