[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"blog:index::Data Engineering":3},{"page":4,"tags":43},{"items":5,"meta":38},[6,18,29],{"id":7,"slug":8,"title":9,"excerpt":10,"tags":11,"read_minutes":16,"published_at":17},"488d06c7-e036-4df1-a0ab-0b5a85fb6cbe","anatomy-of-a-bi-pipeline-airflow-dbt-duckdb-superset","Anatomy of an End-to-End BI Pipeline: Airflow, dbt, DuckDB & Superset","A complete walkthrough of a production-style data pipeline we built for a five-store restaurant chain — incremental extraction to Parquet, a tested dbt warehouse on DuckDB, Airflow orchestration, and seven Superset dashboards. All open-source, all code, with screenshots of every layer.",[12,13,14,15],"Data Engineering","Airflow","dbt","Superset",17,"2026-07-12T00:00:00Z",{"id":19,"slug":20,"title":21,"excerpt":22,"tags":23,"read_minutes":27,"published_at":28},"2c6ce459-fe9d-4d84-97d3-3c489e051dd5","data-engineering-for-llms-rag-pipelines","Data Engineering for LLMs: Building Production RAG Pipelines","Every organization is bolting AI onto its products; few have infrastructure to feed enterprise data into models reliably. Parsing, chunking, metadata, and vector databases — the new ETL.",[24,25,26,12],"AI","RAG","LLM",8,"2026-07-01T00:00:00Z",{"id":30,"slug":31,"title":32,"excerpt":33,"tags":34,"read_minutes":36,"published_at":37},"d5328699-b158-4c93-a106-2bdc4fc8703d","why-dashboards-need-data-pipelines","Your Dashboard Is Only as Good as Its Pipeline","Pretty charts on top of fragile spreadsheets erode trust fast. Why every serious dashboard project should start with an orchestrated, tested data pipeline.",[12,13,14,35],"Analytics",6,"2026-06-18T00:00:00Z",{"has_more":39,"limit":40,"next_offset":41,"offset":42,"total":41},false,24,3,0,[44,47,48,49,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,89,91,93,94,96,98,100,102,103],{"tag":45,"count":46},"Architecture",4,{"tag":24,"count":41},{"tag":12,"count":41},{"tag":14,"count":41},{"tag":13,"count":51},2,{"tag":35,"count":53},1,{"tag":55,"count":53},"Apache Iceberg",{"tag":57,"count":53},"BigQuery",{"tag":59,"count":53},"Careers",{"tag":61,"count":53},"Cloudflare R2",{"tag":63,"count":53},"Cost",{"tag":65,"count":53},"Databricks",{"tag":67,"count":53},"Data Governance",{"tag":69,"count":53},"Data Lake",{"tag":71,"count":53},"Data Quality",{"tag":73,"count":53},"DuckDB",{"tag":75,"count":53},"FinOps",{"tag":77,"count":53},"Flink",{"tag":79,"count":53},"Go",{"tag":81,"count":53},"HLS",{"tag":83,"count":53},"Kafka",{"tag":85,"count":53},"Lakehouse",{"tag":87,"count":53},"Learning",{"tag":26,"count":53},{"tag":90,"count":53},"pgvector",{"tag":92,"count":53},"PostgreSQL",{"tag":25,"count":53},{"tag":95,"count":53},"RBAC",{"tag":97,"count":53},"SkillUp",{"tag":99,"count":53},"Snowflake",{"tag":101,"count":53},"Streaming",{"tag":15,"count":53},{"tag":104,"count":53},"Video"]