'Industry-leading performance across every key observability workload' 🚀 Agent traces are nested, long-running, and full of large payloads.…

"Industry-leading performance across every key observability workload" 🚀 Agent traces are nested, long-running, and full of large payloads. Making them searchable and interactive needs a data layer designed for that shape SmithDB is that data layer. We built SmithDB: the database purpose built for agent observability workloads that now powers many parts of LangSmith. Agent observability presents a challenging data problem. Agent traces can contain tens of thousands of intermediate spans and large, unbounded payloads. These c…

Source: Harrison Chase (X) | 2026-05-13