[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"post-how-to-spot-a-good-software-vendor-and-the-red-flags":3,"$fXeC77ibo_YuG-ZnFG3hwyaNC83zFAKw-FvBNoL2JrIM":15},{"slug":4,"title":5,"excerpt":6,"category":7,"author":8,"readingTime":9,"coverImage":10,"bodyHtml":11,"metaTitle":12,"metaDescription":13,"date":14},"how-to-spot-a-good-software-vendor-and-the-red-flags","How to spot a good software vendor (and the red flags)","You spot a good vendor by what they do before the contract is signed, not by their portfolio. Here are the signs of trust and the warning signs.","How we work","MightCore","8 min",null,"\u003Cp>\u003Cstrong>You spot a good software vendor before they build anything: by whether they ask first, whether they talk about risks, and whether they tell you what is not worth doing. Portfolio and technology come second.\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cp>Choosing a vendor is hard precisely because you only see the quality of the work after months, once the money and time are already spent. But there are signals you can read in advance.\u003C\u002Fp>\n\n\u003Ch2>Good signs before you sign\u003C\u002Fh2>\n\u003Cp>The strongest signal is that they ask \"why\". A vendor who wants to understand your problem before proposing a solution is unlikely to sell you something pointless. Anyone who knows exactly what to build at the first meeting either was not listening or is recycling a past project.\u003C\u002Fp>\n\u003Cp>The second good sign is that they talk about risks. \"This might be harder than it looks\" is not weakness, it is experience. Anyone promising it will all go smoothly either has not done this long enough or is not telling you the truth.\u003C\u002Fp>\n\u003Cp>The third is a willingness to say no. A vendor who occasionally talks you out of what you want is thinking about the outcome, not the invoice. We write about it in \u003Ca href=\"\u002Fblog\u002Fwhere-not-to-use-ai-and-why-nobody-tells-you\">where not to use AI\u003C\u002Fa> — sometimes the best advice is \"do not do this\".\u003C\u002Fp>\n\n\u003Ch2>Red flags\u003C\u002Fh2>\n\u003Cp>Be careful when:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>A price arrives with no questions.\u003C\u002Fstrong> An exact figure for a project nobody has understood yet is guessing dressed up as certainty.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Everything is \"no problem\".\u003C\u002Fstrong> Real development has trade-offs. Anyone who does not mention them either cannot see them or is hiding them from you.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>They cannot explain what they do.\u003C\u002Fstrong> If you leave the answers more confused than before, that is not your fault. A good vendor can make complex things simple.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Code ownership is vague.\u003C\u002Fstrong> It must be in writing that the result is yours and can be handed to somebody else. Without that, you are trapped.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>They will not discuss what happens after handover.\u003C\u002Fstrong> Software has to be maintained. Anyone pretending the project ends at launch is not preparing you for reality.\u003C\u002Fli>\n\u003C\u002Ful>\n\n\u003Ch2>Questions worth asking\u003C\u002Fh2>\n\u003Cp>Ask what happens if the brief changes mid-project — the answer tells you how they approach a partnership. Ask who will maintain the code and who owns it. And ask about a project that did not work out and what they learned from it. Anyone without such a story either has not done enough or is not being honest.\u003C\u002Fp>\n\u003Cp>How the engagement model affects the risk on your side is covered in \u003Ca href=\"\u002Fblog\u002Ffixed-price-or-hourly-which-is-better-for-the-client\">fixed price or hourly\u003C\u002Fa>.\u003C\u002Fp>\n\n\u003Ch2>The takeaway\u003C\u002Fh2>\n\u003Cp>You do not spot a good vendor by how nicely they talk about technology, but by how they approach your problem. We built our whole way of working on the idea that \u003Ca href=\"\u002Fblog\u002Fwhy-context-comes-before-code\">context comes before code\u003C\u002Fa> — and we are happy to show it in practice in a \u003Ca href=\"\u002Fcontact\">free consultation\u003C\u002Fa>.\u003C\u002Fp>","How to spot a good software vendor — and the red flags","How to recognise a reliable software vendor, what questions to ask before signing, and which red flags mean you should be on your guard.","2026-05-20T00:00:00.000Z",[16,23,29,35,40,46,53,59,60,65,69,74,80,85,89,94,99,105,109,114,119,124,130,136,141,146,151,156,161,166,171,176,181,186,191,196,201,206,211,215,220,225],{"slug":17,"title":18,"excerpt":19,"category":20,"author":8,"readingTime":21,"coverImage":10,"date":22},"how-to-talk-to-a-language-model-prompting-in-practice","How to talk to a model: prompting without incantations","Prompt engineering is not a list of magic phrases. It is the ability to say exactly what you want — which is harder than it sounds.","Guides","7 min","2026-07-08T00:00:00.000Z",{"slug":24,"title":25,"excerpt":26,"category":27,"author":8,"readingTime":21,"coverImage":10,"date":28},"how-to-choose-a-language-model-and-control-costs","Choosing a language model and keeping costs under control","Benchmarks tell you almost nothing useful. What actually decides a model choice, and where the costs nobody predicted come from.","Engineering","2026-06-30T00:00:00.000Z",{"slug":30,"title":31,"excerpt":32,"category":27,"author":8,"readingTime":33,"coverImage":10,"date":34},"programming-in-the-age-of-ai-what-actually-changed","Programming in the age of AI: what actually changed","No, it did not replace developers. But it changed where they spend their time — and not all of those changes are comfortable.","9 min","2026-06-17T00:00:00.000Z",{"slug":36,"title":37,"excerpt":38,"category":7,"author":8,"readingTime":39,"coverImage":10,"date":34},"why-we-charge-for-value-not-hours","Why we charge for value, not hours","Billing by the hour rewards slowness and punishes experience. Here is why we look at what a solution brings the business, not what it cost us.","6 min",{"slug":41,"title":42,"excerpt":43,"category":44,"author":8,"readingTime":21,"coverImage":10,"date":45},"ai-modelka-pre-vas-brand-sprievodca","An AI model for your brand: the complete guide","From brief through avatar creation to the first campaign — step by step.","AI UGC","2026-06-16T00:00:00.000Z",{"slug":47,"title":48,"excerpt":49,"category":50,"author":8,"readingTime":51,"coverImage":10,"date":52},"pripadova-studia-cleago","Case study: Cleago — a platform built on context","How we designed and built a solution for Cleago (www.cleago.sk) by first understanding the context and only then coding.","Case studies","5 min","2026-06-02T00:00:00.000Z",{"slug":54,"title":55,"excerpt":56,"category":57,"author":8,"readingTime":39,"coverImage":10,"date":58},"where-not-to-use-ai-and-why-nobody-tells-you","Where not to use AI (and why nobody tells you)","A company selling AI has little incentive to talk about its limits. Let us fix that — these are the places AI simply does not belong.","For business","2026-05-27T00:00:00.000Z",{"slug":4,"title":5,"excerpt":6,"category":7,"author":8,"readingTime":9,"coverImage":10,"date":14},{"slug":61,"title":62,"excerpt":63,"category":44,"author":8,"readingTime":51,"coverImage":10,"date":64},"ai-model-consistent-brand-across-campaigns","A consistent brand with an AI model across campaigns","An AI model can be a brand's steady face — if you handle consistency and transparency the right way. Here is how.","2026-05-19T00:00:00.000Z",{"slug":66,"title":67,"excerpt":68,"category":50,"author":8,"readingTime":51,"coverImage":10,"date":64},"pripadova-studia-produktove-fotky","Case study: 80% less time spent creating product photos","A real example of deploying AI photos in an online store — from brief to results.",{"slug":70,"title":71,"excerpt":72,"category":57,"author":8,"readingTime":9,"coverImage":10,"date":73},"where-ai-actually-fits-in-a-company","Where AI actually fits in a company (and where it is just flashy)","Concrete applications across departments — what works today, what needs preparation, and what is still a demo rather than a tool.","2026-05-06T00:00:00.000Z",{"slug":75,"title":76,"excerpt":77,"category":78,"author":8,"readingTime":39,"coverImage":10,"date":79},"rest-vs-graphql-pre-eshopy","REST vs. GraphQL API for modern online stores","When to choose which approach and what the impact on performance and development is.","Development","2026-04-21T00:00:00.000Z",{"slug":81,"title":82,"excerpt":83,"category":7,"author":8,"readingTime":21,"coverImage":10,"date":84},"fixed-price-or-hourly-which-is-better-for-the-client","Fixed price or hourly: which is better for the client","A fixed price moves the risk to the vendor, hourly moves it to the client. Here is when each fits — and why neither is always the right one.","2026-04-15T00:00:00.000Z",{"slug":86,"title":87,"excerpt":88,"category":57,"author":8,"readingTime":33,"coverImage":10,"date":84},"how-to-bring-ai-into-your-company-first-steps","How to bring AI into your company without wasting the money","Most AI projects do not fail on technology. They fail because nobody said what was supposed to get better. Where to start instead.",{"slug":90,"title":91,"excerpt":92,"category":50,"author":8,"readingTime":39,"coverImage":10,"date":93},"case-study-monolith-to-modular-migration","Case study: from a monolith to a modular architecture with no downtime","An illustrative example of gradually modernising an older application — where every change was risky and maintenance expensive.","2026-04-14T00:00:00.000Z",{"slug":95,"title":96,"excerpt":97,"category":20,"author":8,"readingTime":9,"coverImage":10,"date":98},"ai-agents-and-tool-calling-when-it-makes-sense","AI agents and tool calling: when it makes sense and when it does not","An agent is a model allowed to act. That is interesting and dangerous in equal measure. How it works, and where to be careful.","2026-03-25T00:00:00.000Z",{"slug":100,"title":101,"excerpt":102,"category":103,"author":8,"readingTime":39,"coverImage":10,"date":104},"uctovnictvo-novej-generacie","Next-generation accounting: a platform built on context","A vision of an intelligent layer on top of existing accounting tools.","Accounting","2026-03-17T00:00:00.000Z",{"slug":106,"title":107,"excerpt":108,"category":20,"author":8,"readingTime":39,"coverImage":10,"date":104},"context-driven-development-context-gathering-in-practice","Context Driven Development in practice: how gathering context changes the outcome","The most expensive mistakes come from a misunderstood brief. Here is what the context gathering that prevents them looks like.",{"slug":110,"title":111,"excerpt":112,"category":7,"author":8,"readingTime":39,"coverImage":10,"date":113},"what-happens-in-a-first-software-consultation","What happens in a first consultation, and what you take away","A first consultation is not a sales call. It is an hour spent understanding your problem — and you often leave with a clearer view, even if we never start.","2026-03-11T00:00:00.000Z",{"slug":115,"title":116,"excerpt":117,"category":20,"author":8,"readingTime":33,"coverImage":10,"date":118},"how-to-orchestrate-language-models-in-practice","Orchestrating language models: from one prompt to a system","One prompt is a demo. An application is something else. On splitting work, routing between models, and where to leave ordinary code alone.","2026-03-04T00:00:00.000Z",{"slug":120,"title":121,"excerpt":122,"category":103,"author":8,"readingTime":51,"coverImage":10,"date":123},"digitalising-accounting-e-invoicing","Digitalising accounting: e-invoicing and what it brings","Electronic invoicing and reporting are becoming the standard. What it means for businesses and how to prepare without panic.","2026-02-17T00:00:00.000Z",{"slug":125,"title":126,"excerpt":127,"category":128,"author":8,"readingTime":9,"coverImage":10,"date":129},"what-is-an-llm-large-language-model-explained","What an LLM is: large language models without the mystique","How does a program that predicts the next word end up writing working code? A look at what actually happens inside a language model.","Fundamentals","2026-02-11T00:00:00.000Z",{"slug":131,"title":132,"excerpt":133,"category":134,"author":8,"readingTime":51,"coverImage":10,"date":135},"ako-ai-setri-naklady-na-video","How AI cuts the cost of video content production","Concrete numbers and a workflow for creating AI videos for online stores.","Marketing","2026-02-10T00:00:00.000Z",{"slug":137,"title":138,"excerpt":139,"category":7,"author":8,"readingTime":21,"coverImage":10,"date":140},"why-context-comes-before-code","Why context comes before code","Most software does not fail on the code; it fails because the wrong thing got built. Here is why everything we do starts with understanding the context.","2026-02-04T00:00:00.000Z",{"slug":142,"title":143,"excerpt":144,"category":128,"author":8,"readingTime":21,"coverImage":10,"date":145},"what-is-artificial-intelligence-explained-without-the-marketing","What artificial intelligence is (and what it is not)","The word AI now means everything, and therefore nothing. Here is what is actually behind it, and where technology ends and marketing begins.","2026-01-21T00:00:00.000Z",{"slug":147,"title":148,"excerpt":149,"category":78,"author":8,"readingTime":39,"coverImage":10,"date":150},"vector-databases-and-embeddings","Vector databases and embeddings: how machines grasp meaning","Semantic search sits behind many AI features. Here is what embeddings are and why modern data work rests on them.","2026-01-20T00:00:00.000Z",{"slug":152,"title":153,"excerpt":154,"category":78,"author":8,"readingTime":39,"coverImage":10,"date":155},"trendy-v-ai-vyvoji-2026","Trends in AI development for 2026","What awaits companies in the area of AI agents, automation and infrastructure.","2026-01-14T00:00:00.000Z",{"slug":157,"title":158,"excerpt":159,"category":50,"author":8,"readingTime":51,"coverImage":10,"date":160},"case-study-ai-product-photography-cosmetics","Case study: AI product photography for a cosmetics e-shop","An illustrative example of how AI content replaced repeated photoshoots and brought a consistent visual identity across seasons.","2025-12-09T00:00:00.000Z",{"slug":162,"title":163,"excerpt":164,"category":78,"author":8,"readingTime":39,"coverImage":10,"date":165},"integrating-ai-into-existing-systems","How to integrate AI into existing systems without a rewrite","You do not have to throw away working software to use AI. Here is an approach that adds value step by step, with low risk.","2025-11-18T00:00:00.000Z",{"slug":167,"title":168,"excerpt":169,"category":20,"author":8,"readingTime":21,"coverImage":10,"date":170},"gdpr-a-ai-obsah","GDPR and AI content: what to watch out for","The legal minimum for companies working with AI content and personal data.","2025-11-11T00:00:00.000Z",{"slug":172,"title":173,"excerpt":174,"category":44,"author":8,"readingTime":39,"coverImage":10,"date":175},"virtualne-ai-modelky","Virtual AI models: the future of advertising or a passing trend?","The possibilities, limits and ethics of virtual influencers for brands.","2025-10-20T00:00:00.000Z",{"slug":177,"title":178,"excerpt":179,"category":44,"author":8,"readingTime":51,"coverImage":10,"date":180},"ai-ugc-in-performance-marketing","AI UGC in performance marketing: what works and what applies","How to use AI content in Meta and TikTok campaigns, why creative testing matters, and what AI-labelling rules apply.","2025-10-14T00:00:00.000Z",{"slug":182,"title":183,"excerpt":184,"category":78,"author":8,"readingTime":39,"coverImage":10,"date":185},"llm-hallucinations-how-to-limit-them","LLM hallucinations and how to limit them in practice","Why AI sometimes states nonsense with confidence, and the techniques we use to keep output trustworthy.","2025-09-16T00:00:00.000Z",{"slug":187,"title":188,"excerpt":189,"category":44,"author":8,"readingTime":51,"coverImage":10,"date":190},"co-je-ai-ugc","What AI UGC is and why the whole world is talking about it","An introduction to AI-generated UGC and its impact on advertising and customer trust.","2025-09-15T00:00:00.000Z",{"slug":192,"title":193,"excerpt":194,"category":50,"author":8,"readingTime":39,"coverImage":10,"date":195},"case-study-b2b-eshop-faster-delivery","Case study: a B2B e-shop ready in weeks, not months","An illustrative example of how context gathering and AI execution shortened a wholesale e-shop build — without cutting quality.","2025-08-19T00:00:00.000Z",{"slug":197,"title":198,"excerpt":199,"category":134,"author":8,"readingTime":51,"coverImage":10,"date":200},"ai-v-marketingu-od-experimentu-k-vysledkom","AI in marketing: from experiment to real results","How to move from \"playing with AI\" to a measurable return on investment.","2025-08-06T00:00:00.000Z",{"slug":202,"title":203,"excerpt":204,"category":103,"author":8,"readingTime":51,"coverImage":10,"date":205},"ai-invoice-processing-in-accounting","AI invoice processing: from scan to posting","Intelligent document processing cuts the routine of retyping invoices. How it works and where AI has its limits.","2025-07-15T00:00:00.000Z",{"slug":207,"title":208,"excerpt":209,"category":78,"author":8,"readingTime":39,"coverImage":10,"date":210},"shopsys-vs-vlastne-riesenie","ShopSys vs. a custom build: when a framework pays off","A decision framework for e-shop owners facing the choice of platform.","2025-06-18T00:00:00.000Z",{"slug":212,"title":213,"excerpt":214,"category":20,"author":8,"readingTime":39,"coverImage":10,"date":210},"rag-why-context-decides-ai-quality","RAG: why context decides the quality of AI output","Retrieval-Augmented Generation connects a language model to your own data. Here is how it works and when to use it.",{"slug":216,"title":217,"excerpt":218,"category":134,"author":8,"readingTime":51,"coverImage":10,"date":219},"ako-ai-meni-ecommerce-na-slovensku","How AI is changing e-commerce","Practical examples of AI in product content, search and personalisation for online stores.","2025-05-21T00:00:00.000Z",{"slug":221,"title":222,"excerpt":223,"category":78,"author":8,"readingTime":21,"coverImage":10,"date":224},"context-driven-development-novy-pristup","Context Driven Development: a new approach to building software","An explanation of the CDD methodology from gathering context to deployment — step by step.","2025-04-09T00:00:00.000Z",{"slug":226,"title":227,"excerpt":228,"category":78,"author":8,"readingTime":39,"coverImage":10,"date":229},"koniec-ery-predrazeneho-vyvoja","Why the era of overpriced software development is over","How AI and a context-driven approach are changing the economics of building software — and why paying for inflated hours no longer makes sense.","2025-03-12T00:00:00.000Z"]