Knowledge base
Knowledge sharing on real IT projects. Engineering insights, tutorials, case studies and best practices.
Legal basis, a DPA with the AI provider, EU data residency, pseudonymisation, retention and training opt-out, the balancing test, the AI Act and a checklist.
Prompts are code: repo, versioning, review, template structure, few-shot examples, eval sets, regression tests, injection defence, cost and observability.
OCR + LLM pipeline, JSON-schema extraction, validation with human-in-the-loop, SAP/ERP integration, error-rate tracking and ROI for invoices and contracts.
Six evaluation criteria, a comparison table, recommendations by task type and a router pattern with code: how a company picks an LLM in 2026.
Agent, chatbot or workflow? Where an AI agent pays off for an SMB, where it fails, which guardrails you need, and a 6-week pilot with a cost estimate.
How to build a RAG chatbot on company documents that doesn't make things up: architecture, stack selection, cost estimate and production deployment.
A closer look at three workflow automation platforms: pricing, self-hosting, integration count, vendor lock-in and five concrete use-case recommendations.
How we built an AI lead-classification system for a Central European automotive SMB: architecture, tech decisions and the real lessons of four months.
LLMs hallucinate; that is not a bug but how the models work. Seven proven techniques for raising the precision of production AI systems, with code.
Where Hungarian SMBs stand on AI maturity in 2026: five realistic use cases, typical cost estimates, the ROI maths and three anonymised real projects.