Blog & expertise
AI in production, decoded
Field insights, methods and points of view on industrialising AI: N8N/MCP automation, LLM agents, GenBI, infrastructure and governance.
-
The EU AI Act: a concrete action plan for enterprises in 2026
Obligations, timeline, risk classification: what you actually need to put in place, without panicking or over-investing.
-
Enterprise RAG: why your AI assistants still hallucinate
An assistant that cites a document that doesn’t exist destroys trust in a single demo. The real causes of RAG hallucinations, and…
-
AI project ROI: stop promising it, start measuring it
“30% more productivity” means nothing. How to build a defensible ROI case, from scoping through to production monitoring.
-
AI in production, not in POC: 5 reasons your POCs stall before scaling
Most AI POCs never become products. Here are the five most common causes — and how to defuse them at the scoping…
-
Your data isn’t ready for AI: a 6-point diagnostic
Before training or plugging in an LLM, six checks decide whether your data will hold up or sink the project.
-
GenBI and the semantic layer: the missing link between your data and natural language
Without a shared definition of your metrics, GenBI makes things up. The semantic layer is what separates a flashy demo from a…
-
N8N, MCP and LLM agents: governed automation, not a tangled mess
Orchestrating LLM agents with N8N and MCP without building unmanageable integration debt: architecture principles and concrete guardrails.
-
GenBI: query your data in natural language, without hallucinations
Generative BI promises natural-language querying. The real risk: confidently wrong answers. How to make it safe.
Move from experimentation to AI in production
Start with a short, fixed-price assessment: maturity, high-ROI use cases, and a prioritised roadmap. No commitment.