Retrieval ✦ 69outlineNot a production recipe — calibrate thresholds

NL predicates after SQL

Who: Data apps. Steps: SQL returns rows → Jev Noul/Choice per row → filter/sort in client. Expected effect: Semantic filter without LLM SQL gen.

Source: https://github.com/EugeneBoondock/jevsql ↗ Docs / source ↗

Treat this as an outline — adapt state and questions to your data.

Implement in code — call System One / Jev; compose answers yourself.

Gate on confidence — act, confirm, or escalate before side effects.

Outline sketch

Prompt

# NL predicates after SQL
State: relevant software state for this pattern.
Ask: Choice / Score / Noul questions that close the decision space.
Then: compose the route or action in code; escalate when confidence is low.

Needs access to: typesafe-sdk

Who it's for

Data apps

Steps / how it's set up

Steps

SQL returns rows.
Jev Noul/Choice per row.
filter/sort in client.

Sources

Metrics and demo claims are author-reported or cookbook-reported unless you measure them yourself. Calibrate on your data.

Expected effect

Semantic filter without LLM SQL gen

Unofficial outline for learning. Paraphrased from public docs and tutorials — not a production recipe. Review sources before you automate anything.