// Topics / Data

Data

    AI Data Privacy Is a Plumbing Problem AI privacy fails in the details: what gets logged, who can replay prompts, how long artifacts linger. Treat it as infrastructure, not a checkbox. privacy ai data AI Data Pipelines for RAG: ETL With a Retrieval Layer AI data pipelines are ETL with a retrieval layer bolted on. The discipline is the same as always: detect change, chunk intelligently, keep indexes fresh. data ai infrastructure Video Understanding AI: Transcript First, Frames Second I built a video understanding pipeline for support call review. What worked: transcript first, scene-based frame sampling, timestamps on every claim. llm ai data Data Engineering Patterns: Batch vs. CDC vs. Streaming Batch vs. CDC vs. streaming ingestion, compared from building financial data pipelines at a fintech startup, and how to pick by real latency needs. data metrics architecture MLOps Fundamentals: Fix the Basics Before Buying Tools Most teams buying MLOps tools can't version their training data. Start with dataset versioning, a release checklist, and one monitoring signal. ai devops data Data Mesh: Fix Data Ownership Before Architecture Most data problems are ownership problems. Data mesh gets that right. But adopting it as an architecture diagram exercise misses the point entirely. data architecture engineering GDPR for Engineers: What We Built at a Fintech Startup Eleven days before the GDPR deadline: data mapping, consent records, export and erasure pipelines, and the backup problem at a fintech startup. compliance privacy business Data Pipelines That Survive Production: How I Build Them Every data pipeline I built at a fintech startup broke. Raw storage, idempotent writes, boundary validation, and output-shape alerts made them recoverable. data reliability architecture