Notes on data, AI, IT
and security
No marketing fog. The way I think about real problems with founders and managers.
Five AI questions worth answering before the year ends
2025 changed expectations around AI. I close the year with five questions that help managers honestly assess their readiness for the year ahead.
MCP and managed agents: how to connect to data without writing one-off glue code
The Model Context Protocol changes how agents connect to external systems. I break down what this means for architecture and data management in enterprise.
LLM hallucinations in operational decisions: the risk managers miss
Language models produce confident wrong answers. In internal demos this is inconvenient. In operational decisions it is a liability. I break down where the risk actually sits.
AgentKit and agentic UX as a new layer of enterprise software
Agentic interfaces are changing how enterprise software looks and works. I break down what this means for architectural decisions and UX strategy.
How to evaluate the return on AI investments: questions before the decision
ROI of AI projects is measured differently than ROI of traditional automation. I break down the right questions to ask before money is spent.
Long context in LLMs: what changes for architects and decision-makers
Models with hundred-thousand-token context windows look like a solution to many problems. I break down what this actually changes in practice - and where the traps are.
The coding agent and the new assembly point of development
GitHub Copilot is becoming an agent that can execute development tasks autonomously. What this changes for companies that commission or run software development.
Context windows and knowledge management in a company
How growing language model capabilities affect how companies can organise access to corporate knowledge.
AI agent systems: moving from demo to platform
New tools for building AI agents are changing the conversation from 'is this possible' to 'how do we manage this in production'.
RAG in production: what architects actually need to decide
Retrieval-augmented generation has become the default pattern for corporate AI. I break down what architectural decisions actually matter and where the traps are.
The EU AI Act: where the red zone starts for business
The first binding rules of the EU AI Act on prohibited practices came into force in February 2025. What this means for companies using or planning to use AI.
DeepSeek-R1: reasoning as a new dimension of competition
What the release of DeepSeek-R1 means for companies thinking about AI: cost, openness, and practical consequences.