What we learn on projects: architecture, tools, traps, and what we solved.
Three months in. SZEP 2.0 live, NAV v3 cutover, AI Act enforcement, OWASP LLM Top 10 v2. Hard numbers, one strong opinion on the consulting tier.
Short answer: yes, and it's simpler than most people fear. One natural sentence at the start of the call does it — here's the rule, the timing, and how we build it.
Garages lose jobs to unanswered calls, especially at tyre-change and MOT peaks. How an AI receptionist books every slot 24/7.
Every missed call is a lost patient. How an AI receptionist answers 24/7, books, and cuts no-shows, plus the honest ROI and cost.
What an AI phone agent actually does on a live call, how the speech pipeline works, honest cost ranges, and the build-vs-buy decision.
Four months in. Eleven shipped projects, real before/after numbers, one strong opinion on what the consulting tier got wrong this quarter.
No-code automation is brilliant until it isn't. Here's the line where n8n / Make stop saving money and custom code starts - and how to tell which side you're on.
An AI agent is not a chatbot with extra steps - it takes actions, and that changes the bill. Here are the real 2026 ranges and what drives them.
Four shifts defined the first half of 2026 for EU software teams. Here's what changed, what it means, and what to do about each one.
Logistics is one of the few fields where AI pays for itself fast - if you point it at the right problem. Here's where it works for Hungarian operators in 2026.
The honest answer in 2026: start with PostgreSQL, reach for MongoDB only when your data and access pattern genuinely demand it. Here's how to tell.
If you're a US or UAE company weighing a European engineering partner, the decision isn't really about rates · it's time zones, who owns the IP, and whether EU compliance is a tax or a feature. Here's the honest breakdown.
The EU AI Act is phasing in, it reaches companies far outside the EU, and most of the work is engineering, not legal. Here's how a build team should actually think about it in 2026.
Most teams buy a penetration test without knowing what a good one produces. Here's what should be in scope, what the deliverable looks like, and the red flags that mean you bought an automated scan with a nicer cover page.
A smart-contract bug is permanent and the funds are real. Here's the engineering checklist a contract should clear before it touches mainnet - exploit classes, real testing, the audit, and a careful deploy.
Vague briefs get vague quotes - and the gap shows up later as a budget overrun. Here's how to write a one-page brief that gets accurate numbers back and reveals which studio actually fits.
Search is shifting from ten blue links to one synthesised answer with citations. Generative engine optimization is how you become one of those citations - and most of it is engineering, not copywriting.
Most companies default to "build an app" before asking whether they need one. A PWA is often the cheaper, faster answer - and sometimes it isn't. Here's how to decide before you spend the budget.
Calling the OpenAI or Anthropic API is the right default for most AI features. But data sensitivity, steady high volume, or strict EU residency can flip the answer. Here's the honest decision.
Strip away the speculation and blockchain does one useful thing: it makes a record nobody can quietly change. Here's where that's worth paying for - and where a plain database wins.
One sentence is enough. EN or HU.