semantic-jev: natural-language queries through a semantic layer
A CLI routes natural-language questions through a Cube or dbt semantic layer with Jev confidence checks, so only safe, verified queries run on production data.
A CLI routes natural-language questions through a Cube or dbt semantic layer with Jev confidence checks, so only safe, verified queries run on production data.
A worked guide to Jev's Score primitive: writing a request, defining rubric levels, reading recorded probabilities and the weighted-score math.
Jev Trader · Research & data
Jev Trader
Guide
Research & data
-
-
Sends a detected bot's last 48 request paths to Jev, which picks what it's after (prices, articles…) and how it crawls (pagination, IDs…), or unknown.
WebDecoy · Research & data
WebDecoy
Resource
Research & data
-
-
Paste an article or post link. Fake / Real extracts its claims, finds outside evidence, and has Jev judge whether the evidence supports or contradicts each one.
@DansiDanutz · Research & data
@DansiDanutz
Site
Research & data
-
-
Combines rubric science and LLM-as-a-judge research to grade outputs with AI judges: LLMs, decision models like Jev, or both.
@deliprao · Research & data
@deliprao
Site
Research & data
-
-
Stop letting LLMs or Jev write raw SQL against production data or even evaluate rows. I built a CLI that routes questions through a semantic layer (Cube/dbt) with confidence checks so it only runs safe, verified queries. Quick demo running on: github.com/johnnymakhoul/…