Agents
Managing and monitoring agents will require us to rethink infrastructure since most systems were not designed to support agent scale. Very c…
Managing and monitoring agents will require us to rethink infrastructure since most systems were not designed to support agent scale. Very cool to see how @LangChain leveraged @SpiralDB and other tool
Managing and monitoring agents will require us to rethink infrastructure since most systems were not designed to support agent scale. Very cool to see how @LangChain leveraged @SpiralDB and other tools to support fine-grained agent observably at scale. 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) | 2026-05-22