jevbooks

← All projects

IntentSQL

Amine-LG/IntentSQL

Natural-language SQLite interface using Jev for inspectable query plans.

Agent Decisions0.76Runner-up: Verification & GuardrailsQuestionnaire
Automated README summary

Automatically summarized from the README on 10 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

IntentSQL turns plain English questions about a SQLite database into deterministic SQL by making small Jev decisions instead of generating SQL. It is for users who want to see and verify every step.

How it uses Jev

Jev answers multiple-choice questions about which column, filter, grouping, sort, or join the user meant. Code builds all options, Jev picks in one parallel round, and the answers are assembled into a typed plan that compiles to parameterized SQLite.

Primitives:choice

Technique worth stealing

Code proposes all reasonable options; Jev chooses among them; code builds the SQL.

Try it

pip install . && intent-sql serve

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.90
  • Shows a System One patternFound in material0.87
  • Describes handling uncertaintyunclear0.48
  • Reports measured numbersFound in material0.88
  • Is a runnable toolunclear0.42
  • Top-10 learning shortlist signalunclear0.55
  • Is a replica of the modelnot found in the excerpt0.06
  • Solves a common problem (0–2)score on a 0–2 scale1.06 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.90Shows a System One pattern0.87Describes handling uncertainty0.48Reports measured numbers0.88Is a runnable tool0.42Top-10 learning shortlist signal0.55Is a replica of the model0.0600.51Solves a common problem (0–2)1.06 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.80Funnel0.58Check-up0.58Prefetch0.53Inspection0.31Menu0.2600.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 10 Oct 2026.