Lunares — Modern Lighting e-commerce
A fast, SEO-optimised online store for modern lighting — 100,000+ indoor and outdoor lamps, fixtures and home décor, delivered across Europe.
Visit site Kraków, Poland · Software & AI
Software engineering, focused on your goals.
A lean software studio from Kraków, Poland. We build pragmatic web products and weave AI into them — shipped simply, tested thoroughly, and always ready to change.
How we work
Embrace change
Lean design stays ready for your next requirement — not just today's.
Amplify learning
We (ab)test ideas as early as possible and let real data decide.
Share knowledge
The border between your team and ours blends quickly. We teach as we build.
Value simplicity
Simple means fast, reliable, and cheap to maintain.
What we do
We are a small team of senior software engineers. Our mission is to reach your goals in a simple, cost-effective way using modern technology. Working in an Agile, Lean way lets us pivot early and adapt as requirements change — while test-driven development keeps your application robust and a joy to maintain. Increasingly, that means designing AI into products thoughtfully, where it earns its place.
Tech we reach for
- Ruby on Rails
- JavaScript
- PostgreSQL
- MongoDB / NoSQL
- AWS
- CI/CD & DevOps
- LLM & AI integration
- AI agents
- Responsive / mobile web
Our work
Products we build and run — we are our own best customers.
Insureo — Online business insurance
A Polish platform to buy business and professional insurance entirely online — company & professional liability and property cover, quoted in minutes.
Visit siteFrom the blog
Notes on software engineering, AI, and building products.
1 min read
▶ Video
What we learned shipping AI agents to production
Agents are fun in a demo and humbling in production. Here are the guardrails that made ours reliable enough to trust.
8 min read
Building reliable tools for LLMs
Function calling, agents, and MCP all rest on the same thing: tools an LLM can invoke. But a tool built for a non-deterministic, fallible caller needs different design than one built for code. A deep-dive on what makes a tool reliable for an LLM — naming, scope, validation, error messages it can recover from, and the safety that can't live in the model.
7 min read
The AI-native Rails stack in 2026
Put the pieces together — the no-Redis Solid stack, Kamal, pgvector, and the hard-won disciplines of building with LLMs — and a coherent picture emerges: Rails is an outstanding host for AI-native applications, precisely because it lets a small team build and run both the app and its AI features. A synthesis of where the stack stands.