The Semantic Layer Generator: When Agentic AI Meets Data Architecture
How a 5-phase autonomous pipeline eliminates weeks of manual data modelling — and why it matters for every analytics team shipping at scale.
Data Architecture · Data Engineering · AI Engineering
Blueprints for modern data & AI platforms
Diagram-first deep dives on designing data platforms, building reliable pipelines and shipping AI systems to production.
New The Semantic Layer Generator: When Agentic AI Meets Data ArchitectureLatest
Recent articles
Applying AI in Data Engineering - the Agentic Data Engineering
How to apply Agentic AI principles and processes to ease the frictions of the current state of data engineering
Anatomy of a Production RAG System
Retrieval-augmented generation is easy to demo and hard to run. A walkthrough of the offline indexing path, the online query path and the evaluation loop that ties them together.
Idempotent Data Pipelines: Making Re-runs Boring
Retries and backfills are inevitable. Design pipelines so that running them twice gives exactly the same result as running them once.
Designing a Lakehouse with the Medallion Architecture
How to structure raw, refined and curated layers so a lakehouse stays trustworthy, debuggable and cheap to evolve.
Topics
Three pillars of the modern data & AI stack
Data Architecture
Lakehouses, warehouses, data mesh, modelling and the design decisions behind modern data platforms.
2 articles
Data Engineering
Pipelines, streaming, orchestration, data quality and the craft of moving data reliably at scale.
2 articles
AI Engineering
LLM applications, RAG, agents, evaluation and MLOps — putting AI systems into production.
1 article
Never miss a new chapter
Subscribe with any feed reader to get new articles as soon as they are published.