Tag
The article shares lessons learned from operating petabyte-scale ClickHouse clusters for five years, discussing best practices and promoting Tinybird's managed data services.
DBA-Bench is a production-fidelity benchmark for evaluating LLM-based database agents, featuring 106 scenarios across seven domains with outcome-first evaluation and controlled reproducibility. The best automated baseline achieves only 17.9% Safe Pass compared to 93.4% for human DBAs.