SAP Solution Architect · 15+ years · Helsinki, Finland
"In the dark night of all beings awakes to Light the tranquil man. But what is day to other beings is night for the sage who sees." — Bhagavad Gita
RAG is the most important technique for making AI reliable in enterprise settings. It gives an LLM access to your documents, data and knowledge at query time — so it answers from evidence, not from memory. This post explains what RAG is, how it works step by step, where vector databases fit in, and how SAP uses it in Joule and AI Core.
ChatGPT, Claude, Gemini, Joule — they are all powered by large language models. But what is an LLM actually doing when it responds to you? This post explains what an LLM is, how it is trained, what tokens and embeddings mean, and why LLMs predict rather than think — clearly, without the academic language.
SAP Business Technology Platform is the foundation of SAP's cloud strategy — but it can be hard to get a clear picture of what it actually is and what it does. This post explains BTP plainly: what the platform is, its four main pillars, the key services within each, and how it fits into a modern SAP landscape.
Every RAG system runs on a vector database. This post explains embeddings, semantic search and cosine similarity — no prior knowledge of AI or databases required.
This post explains how generative AI works — tokens, embeddings, the transformer and self-attention. The mechanics behind every LLM, explained without a single equation.
Fine-tuning, prompt engineering and RAG each solve a different problem. Pick the wrong one and you waste time and money. This post explains what each does and when to use it.
78% of organisations use AI. But what are they actually doing? This post maps real enterprise AI in 2026 — copilots, code generation, knowledge search, process automation and agents — where it works and where it fails.
RAG is the most important technique for making AI reliable in enterprise settings. It gives an LLM access to your documents, data and knowledge at query time — so it answers from evidence, not from memory. This post explains what RAG is, how it works step by step, where vector databases fit in, and how SAP uses it in Joule and AI Core.
AI hallucinations are not a bug that will be fixed in the next model update. They are a structural consequence of how large language models work. This post explains what hallucination actually is, why it happens at a technical level, the different types, and what practical steps reduce it — without the hype or the panic.
Areas where I design, build, and advise.
End-to-end solutions on SAP Business Technology Platform — integration, extension, and cloud-native development.
Designing and building intuitive Fiori apps that put the user at the centre of every SAP interaction.
Embedding AI capabilities into SAP landscapes — from BTP AI services to custom LLM integrations.
Architecture, migration planning, and implementation of SAP S/4HANA across industries and deployment models.
Guiding organisations through SAP-led transformation — from strategy and roadmap to go-live and adoption.
Making complex SAP concepts accessible — architecture documents, how-to guides, and developer content.
"I spent over a decade building SAP systems in India, then moved to Helsinki. That shift — between two very different ways of working and living — changed how I think about technology, people, and what good architecture really means."
Previously with Accenture; currently at Vivicta (formerly TietoEvry).
Read my story