[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"post-how-to-choose-a-language-model-and-control-costs":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-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","MightCore","7 min",null,"\u003Cp>The first question is usually \"which model is best?\". Understandable, and a dead end. There is no best model. There is the cheapest model that still does your job.\u003C\u002Fp>\n\n\u003Ch2>Why benchmarks will not help\u003C\u002Fh2>\n\u003Cp>Tables of percentages look authoritative, and deciding by them is a mistake.\u003C\u002Fp>\n\u003Cp>First, they test something other than what you need. That a model solves maths olympiad problems tells you nothing about whether it will pull the right registration number off a blurry invoice.\u003C\u002Fp>\n\u003Cp>Second, the differences at the top are small and they move every couple of months. The model that led in March is third in May and half price in July. Basing a decision on today's leaderboard means redoing it every quarter.\u003C\u002Fp>\n\u003Cp>The only benchmark worth anything is your own: take fifty real cases from your business, run them through three models, compare. It costs one afternoon and tells you more than every table combined.\u003C\u002Fp>\n\n\u003Ch2>What actually decides it\u003C\u002Fh2>\n\u003Cp>In our order of importance:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Can it do the job at all?\u003C\u002Fstrong> Test on your data. If a small model can, the discussion is over — take the small one.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>How fast?\u003C\u002Fstrong> If a user is waiting, two seconds is not twenty. If it is an overnight batch, who cares.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>What will it cost at real volume?\u003C\u002Fstrong> Not at demo volume. Multiply by the actual monthly call count.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Where does the data go?\u003C\u002Fstrong> With sensitive material this can decide it before anything else does.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Can you swap it?\u003C\u002Fstrong> The most important item on the list.\u003C\u002Fli>\n\u003C\u002Ful>\n\n\u003Ch2>Replaceability beats the choice itself\u003C\u002Fh2>\n\u003Cp>The market moves too fast to commit to anyone.\u003C\u002Fp>\n\u003Cp>In practice that means one thing: keep a thin layer in your code that every call goes through. Not one provider's SDK scattered across twenty files. When a model arrives in six months at half the price, you want to change one file, not twenty.\u003C\u002Fp>\n\u003Cp>That same layer, incidentally, gives you retries, timeouts, cost accounting and a fallback provider for when the first one goes down. Worth writing while it is still an hour of work.\u003C\u002Fp>\n\n\u003Ch2>Where the cost comes from\u003C\u002Fh2>\n\u003Cp>You pay for tokens in and tokens out, and output tokens are typically much more expensive. That has direct consequences:\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Long conversations get expensive fast.\u003C\u002Fstrong> The model remembers nothing, so every call resends the entire history. The tenth question in a chat costs several times the first — not because it is harder, but because nine earlier ones travel with it.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>The system prompt is resent every time.\u003C\u002Fstrong> Those two pages of instructions you are proud of are billed on every single call.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>\"Explain your reasoning\" is not free.\u003C\u002Fstrong> Let the model think out loud and you pay for every word of the thinking.\u003C\u002Fp>\n\n\u003Ch2>What genuinely works\u003C\u002Fh2>\n\u003Cp>Ordered by effect per unit of effort:\u003C\u002Fp>\n\u003Col>\n\u003Cli>\u003Cstrong>Cache responses.\u003C\u002Fstrong> Boring and the most effective. The same questions repeat more than you think. An answer served from cache costs nothing.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Route to a smaller model.\u003C\u002Fstrong> Classification and extraction do not need the flagship. The gap is often an order of magnitude.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Use prompt caching.\u003C\u002Fstrong> Providers can discount the repeated part of a prompt — put stable instructions first and changing data last.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Send less.\u003C\u002Fstrong> Do not send the whole document when three paragraphs will do. This is, incidentally, exactly the problem RAG solves.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Trim history.\u003C\u002Fstrong> Summarise older turns instead of resending them verbatim.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Batch what can wait.\u003C\u002Fstrong> Providers offer a cheaper tier for work that is not urgent.\u003C\u002Fli>\n\u003C\u002Fol>\n\n\u003Ch2>Measure from day one\u003C\u002Fh2>\n\u003Cp>If you do only one thing from this article, do this one — the rest you will work out yourself.\u003C\u002Fp>\n\u003Cp>Log on every call: which model, tokens in, tokens out, how long it took, which feature it belonged to. Without that you cannot tell whether one feature is bleeding you or a thousand small ones are, and you will optimise blind.\u003C\u002Fp>\n\u003Cp>And set a ceiling. A runaway agent loop or a badly written cycle can spend a monthly budget overnight. This is not hypothetical; it has happened to enough companies that providers now ship their own limits.\u003C\u002Fp>","Choosing a language model and controlling cost","How to pick a language model for production, why benchmarks mislead, how token costs actually work, and what genuinely reduces them.","2026-06-30T00:00:00.000Z",[16,22,23,29,35,42,49,54,58,64,70,75,80,85,90,95,100,105,111,117,122,127,132,137,142,147,152,157,162,167,172,177,182,187,191,196,201],{"slug":17,"title":18,"excerpt":19,"category":20,"author":8,"readingTime":9,"coverImage":10,"date":21},"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","2026-07-08T00:00:00.000Z",{"slug":4,"title":5,"excerpt":6,"category":7,"author":8,"readingTime":9,"coverImage":10,"date":14},{"slug":24,"title":25,"excerpt":26,"category":7,"author":8,"readingTime":27,"coverImage":10,"date":28},"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":30,"title":31,"excerpt":32,"category":33,"author":8,"readingTime":9,"coverImage":10,"date":34},"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":36,"title":37,"excerpt":38,"category":39,"author":8,"readingTime":40,"coverImage":10,"date":41},"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":43,"title":44,"excerpt":45,"category":46,"author":8,"readingTime":47,"coverImage":10,"date":48},"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","6 min","2026-05-27T00:00:00.000Z",{"slug":50,"title":51,"excerpt":52,"category":39,"author":8,"readingTime":40,"coverImage":10,"date":53},"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.","2026-05-19T00:00:00.000Z",{"slug":55,"title":56,"excerpt":57,"category":33,"author":8,"readingTime":40,"coverImage":10,"date":53},"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.",{"slug":59,"title":60,"excerpt":61,"category":46,"author":8,"readingTime":62,"coverImage":10,"date":63},"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.","8 min","2026-05-06T00:00:00.000Z",{"slug":65,"title":66,"excerpt":67,"category":68,"author":8,"readingTime":47,"coverImage":10,"date":69},"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":71,"title":72,"excerpt":73,"category":46,"author":8,"readingTime":27,"coverImage":10,"date":74},"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.","2026-04-15T00:00:00.000Z",{"slug":76,"title":77,"excerpt":78,"category":39,"author":8,"readingTime":47,"coverImage":10,"date":79},"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":81,"title":82,"excerpt":83,"category":20,"author":8,"readingTime":62,"coverImage":10,"date":84},"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":86,"title":87,"excerpt":88,"category":20,"author":8,"readingTime":47,"coverImage":10,"date":89},"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.","2026-03-17T00:00:00.000Z",{"slug":91,"title":92,"excerpt":93,"category":94,"author":8,"readingTime":47,"coverImage":10,"date":89},"uctovnictvo-novej-generacie","Next-generation accounting: a platform built on context","A vision of an intelligent layer on top of existing accounting tools.","Accounting",{"slug":96,"title":97,"excerpt":98,"category":20,"author":8,"readingTime":27,"coverImage":10,"date":99},"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":101,"title":102,"excerpt":103,"category":94,"author":8,"readingTime":40,"coverImage":10,"date":104},"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":106,"title":107,"excerpt":108,"category":109,"author":8,"readingTime":62,"coverImage":10,"date":110},"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":112,"title":113,"excerpt":114,"category":115,"author":8,"readingTime":40,"coverImage":10,"date":116},"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":118,"title":119,"excerpt":120,"category":109,"author":8,"readingTime":9,"coverImage":10,"date":121},"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":123,"title":124,"excerpt":125,"category":68,"author":8,"readingTime":47,"coverImage":10,"date":126},"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":128,"title":129,"excerpt":130,"category":68,"author":8,"readingTime":47,"coverImage":10,"date":131},"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":133,"title":134,"excerpt":135,"category":39,"author":8,"readingTime":40,"coverImage":10,"date":136},"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":138,"title":139,"excerpt":140,"category":68,"author":8,"readingTime":47,"coverImage":10,"date":141},"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":143,"title":144,"excerpt":145,"category":20,"author":8,"readingTime":9,"coverImage":10,"date":146},"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":148,"title":149,"excerpt":150,"category":33,"author":8,"readingTime":47,"coverImage":10,"date":151},"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":153,"title":154,"excerpt":155,"category":33,"author":8,"readingTime":40,"coverImage":10,"date":156},"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":158,"title":159,"excerpt":160,"category":68,"author":8,"readingTime":47,"coverImage":10,"date":161},"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":163,"title":164,"excerpt":165,"category":33,"author":8,"readingTime":40,"coverImage":10,"date":166},"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":168,"title":169,"excerpt":170,"category":39,"author":8,"readingTime":47,"coverImage":10,"date":171},"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":173,"title":174,"excerpt":175,"category":115,"author":8,"readingTime":40,"coverImage":10,"date":176},"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":178,"title":179,"excerpt":180,"category":94,"author":8,"readingTime":40,"coverImage":10,"date":181},"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":183,"title":184,"excerpt":185,"category":20,"author":8,"readingTime":47,"coverImage":10,"date":186},"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.","2025-06-18T00:00:00.000Z",{"slug":188,"title":189,"excerpt":190,"category":68,"author":8,"readingTime":47,"coverImage":10,"date":186},"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.",{"slug":192,"title":193,"excerpt":194,"category":115,"author":8,"readingTime":40,"coverImage":10,"date":195},"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":197,"title":198,"excerpt":199,"category":68,"author":8,"readingTime":9,"coverImage":10,"date":200},"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":202,"title":203,"excerpt":204,"category":68,"author":8,"readingTime":47,"coverImage":10,"date":205},"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"]