LatestAI Delivery
Permission-Aware RAG: Propagating ACLs into a Vector Index
Why filtering RAG results by ACL collapses recall to 39.7%, how Jira and Confluence permissions really resolve, and the three architectures that survive audit.
Data & AI Insights
Thoughts on AI delivery, data architecture, and technical leadership. Practical insights from building real systems.
All Articles
Filter by topic
Data Architecture
Data Governance for Engineers: Building Compliance That Ships with the Code
GDPR right-to-erasure in denormalised warehouses, PII detection at ingestion, governance as code in CI, and the audit questions your platform cannot answer.
Data Architecture
Data Pipeline Engineering: Production Patterns That Survive the First Year
ETL vs ELT tradeoffs, data contracts in CI, schema evolution without pipeline fires, and the failure taxonomy from operating pipelines at enterprise scale.
Data Architecture
Real-Time Data Streaming: When You Actually Need It and How to Build It
Kafka 4.0 with KRaft, Flink vs Kafka Streams tradeoffs, exactly-once semantics in practice, and the cost equation that decides whether streaming is worth it.
AI Delivery
Building the Work Brain: A Glean Alternative in a Weekend
Self-hosted RAG over 45,349 Jira and Confluence documents for €60/month on AWS. Hybrid search, Reciprocal Rank Fusion, pgvector, and the mistakes I made first.
AI Delivery
RAG Architecture That Actually Works in Production
Beyond the tutorials: practical RAG patterns for enterprise systems. Chunking strategies, retrieval architecture, and evaluation frameworks from deployments.
AI Delivery
Multi-Agent Systems: Patterns That Ship to Production
Architecture patterns, coordination strategies, and hard-won lessons from building multi-agent AI systems that actually work. Not theory; production patterns.
Data Architecture
Data Observability: The Engineering You're Probably Missing
Why your data pipelines break silently and how to fix it. A practitioner's guide to monitoring, alerting, and incident response for production data platforms.
AI Delivery
Model Context Protocol (MCP): A Practical Guide for Enterprise AI
What MCP is, why it matters for enterprise AI integration, and practical patterns for implementation. A no-hype guide to connecting AI models with your systems.
Data Architecture
Modern Data Architecture Patterns That Actually Scale
The data architecture decisions that matter in 2026. From warehouse selection to pipeline design, patterns from platforms handling real enterprise workloads.
AI Delivery
Building Production AI Agents: Lessons from Real Deployments
Moving beyond demos to production-ready AI agents. Architecture decisions, observability patterns, and lessons from deploying agents that actually work.
Data Architecture
Choosing the Right Database: A Practitioner's Framework
How to select databases for enterprise workloads. Beyond the benchmarks and vendor marketing, a practical framework for decisions that stick.
AI Delivery
From POC to Production: Why Most AI Projects Fail (And How to Fix It)
Why AI initiatives stall, and the engineering and organizational practices that rescue them. Lessons from projects that shipped and from ones that didn't.