ClickHouse

Headlines · 3

1. 3d
   Mastra introduces span queries for granular agent trace observability

   Mastra announced span queries, which filter and group individual spans across all traces rather than returning whole traces like trace queries do. According to the Mastra Blog, a query can combine up to 100 conditions on fields such as spanType, entityName, status, durationMs and parentEntityName, return up to 1,000 spans per page, and group by up to two dimensions over a time range of up to 365 days, aggregating counts, error rates and latency. The feature is available through the Mastra CLI ([email protected] or later), the Mastra platform and Studio, the Mastra Client SDK (@mastra/[email protected] or later), and observability endpoints, and works on self-hosted projects using DuckDB, PostgreSQL or ClickHouse storage.

   Mastra Blog · 🔥 0
2. Oct 21
   Database expert Andy Pavlo on agent guardrails, vibe-coded databases and LLM tuning

   InfoQ Chinese published an edited transcript of a MAD Podcast conversation between Carnegie Mellon professor Andy Pavlo, now vice president of database research at ClickHouse, and host Matt Turck on how AI agents are reshaping database work. Pavlo argues that agents wiping production databases is an old problem resurfacing — permissioning and control mechanisms have existed for decades — and recommends isolating agents with restricted permissions and branch-based sandboxes rather than approving every action by hand. He also offers rough figures: off-the-shelf text-to-SQL tools reach about 60% accuracy, LLM-based database tuning gets roughly 80-85% of the way, and more than 60% of open-source database systems now show agent-authored commits in his dbdb.io tracking.

   InfoQ 中文 AI&大模型 · 🔥 0
3. Oct 14
   Mastra launches Trace Queries for filtering agent traces

   Mastra introduced Trace Queries, letting users of the Mastra platform and local Studio filter and find traces by fields such as time, primitive name, agent or workflow ID, status, score and feedback. The company says the same queries can be built through the CLI ([email protected] or later), the Mastra Client SDK (@mastra/[email protected] or later) and HTTP observability endpoints. Each query covers a time range of up to 31 days, combines up to 100 conditions and allows up to 8 filters on trace internals such as spans, scores and feedback; the feature works on the Mastra platform and on self-hosted projects whose observability storage uses DuckDB, PostgreSQL or ClickHouse, and existing history can be brought in via trace imports.

   Mastra Blog · 🔥 0

Experience and discussion from the community

Share my ClickHouse experienceAsk about ClickHouse