YAML-first, domain-driven data governance for AI agents — teach agents your business domains, metrics, and rules before they write SQL

A standalone data quality/QA project: SQL validation queries + Great Expectations suite on a synthetic timesheet dataset.

Eval-driven SQL reliability for AI agents — generate, validate, safely execute, and regression-test LLM SQL. MCP + FastAPI gateways, execution-truth evals, CI regression gate.

QA portfolio project demonstrating API testing, SQL validation, and Python automation using DummyJSON E-Commerce API, Postman, SQLite, requests, and pytest.

Production-grade evaluation framework for Text-to-SQL and SQL AI agents with 50+ correctness metrics.

A new package that helps developers ensure column safety in SQLite queries by analyzing and validating their SQL statements. The package takes a user's SQL query as text input and returns a structured

Reproducible evaluation of schema-grounded Text-to-SQL using BIRD Mini-Dev, with schema retrieval, SQL validation, bounded repair, abstention, and read-only SQLite execution.

Two-stage LLM-based Text-to-SQL framework with schema retrieval, SQL validation, and self-correction.

Governed, template-based text-to-SQL for manufacturing: pre-approved SQL templates, a multi-rule validator, and full audit logging, exposed via an MCP server and a no-API-key CLI.

Airflow + Postgres DQ platform: observability, rule-based monitoring (SQL+JSON), pluggable alerting, Metabase dashboards.

Deterministic semantic verification for agent-generated SQL.

Production-style Flask backend for safe natural-language-to-SQL analytics using OpenAI, SQLite, SQL validation, audit logging, Redis rate limiting, Docker, and pytest.