How an LLM works: from your question to the first word
Tokens, attention, KV cache: opening the black box, diagram by diagram, to design better AI projects and keep their costs under control.
Read the articleThe blog
What we learn in the field.
Articles written by the team, about the questions we run into on engagements: data, AI, cloud. Without jargon whenever possible.
Articles
DataOps: finally bringing DevOps practices to data engineering
CI/CD for data pipelines, Data Quality as Code, observability: the three pillars of DataOps, the tools (dbt, Great Expectations, Soda, Monte Carlo, OpenTelemetry) and Logbrain's recommended practices.
16 October 2026
.png)
Data Mesh: beyond the hype, what actually works in the field
Data Mesh: the 4 principles, the 3 pitfalls that sink projects, and the success factors observed in banking, industry and retail. Lessons from Logbrain's field experience.
16 October 2026
AI workflows and agents: choose for the problem, measure the value
An AI agent can explore a situation, use tools and adapt its actions. A workflow can organise a reliable, repeatable process. The right choice depends on the problem, your constraints and the benefit you can actually measure.
01 October 2026
Shall we talk?
A project, a question, a doubt about an architecture: email us or book a slot. The first conversation is for understanding, not selling.