Log inSign up
Image
user avatar
Databend
@DatabendLabs
Agent-ready Warehouse for analytics, search, AI, and Python Sandbox. Databend Cloud: app.databend.com/login GitHub: github.com/databendlabs
SF
databend.com
Joined September 2021
133
Following
2,117
Followers
RepliesMedia
  • Pinned
    user avatar
    Databend
    @DatabendLabs
    Jul 1
    Agent trace is not traditional observability trace. Traditional trace: seconds/minutes, stable schema, latency/status/error. Agent trace: minutes/hours, nested JSON, schema drift, tool calls, model outputs, token cost, branch points. That changes the data layer. You need
    Image
  • user avatar
    Databend
    @DatabendLabs
    Jul 30
    Snowflake teams keep revisiting the FinOps loop: right-size warehouses, tune auto-suspend, audit queries, assign cost owners. Databend Cloud starts simpler: transparent pay-as-you-use compute, open Parquet, 90%+ Snowflake SQL parity, and BYOC. Compare 👉 bit.ly/4bnDz2h
    Image
  • user avatar
    Databend
    @DatabendLabs
    Jul 28
    Global sorts make optimizer stats accurate and expensive. Databend combines KLL for one-pass quantiles, Top-N for exact hot values, and CMS for a wider hot set. In our benchmark, CMS cut equality q-error from 25.354 to 1.355. 🚀 Deep dive: bit.ly/4pKP3my
    Image
  • user avatar
    Databend
    @DatabendLabs
    Jul 23
    Filtering a window function shouldn’t require another query layer. QUALIFY keeps ranking and filtering together for deduplication, latest rows, and Top N per group. Cleaner SQL. Faster reviews. See 6 practical patterns in Databend 👉bit.ly/4yIMLZh #DataEngineering
    Image
  • user avatar
    Databend
    @DatabendLabs
    Jul 21
    When agent traces reach TB scale, is “observability” still the right mental model? They’re also eval datasets, replay records, and training feedback. Should teams build the underlying data infrastructure themselves, or use a platform like Databend? Here’s a deep dive into the
    Image

  • See @DatabendLabs's full profile

    Sign up
    Log in