[
    {
        "id": "osp-23494",
        "type": "article-journal",
        "title": "An Iterative LangGraph Agent for Text-to-SQL: Natural Language Access to the Chicago Crime Database",
        "author": [
            {
                "family": "Rao",
                "given": "Vigneshwar Ravi"
            },
            {
                "family": "Swarnakar",
                "given": "Rupesh"
            },
            {
                "family": "Syed",
                "given": "Fayeq Jeelani"
            }
        ],
        "URL": "https://omanscience.com/en/articles/an-iterative-langgraph-agent-for-text-to-sql-natural-language-access-to-the-chicago-crime-database",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Non-technical stakeholders frequently cannot write the SQL needed to extract insights from operational databases. We built and evaluated a Text-to-SQL agent that closes this gap end to end: a six-node LangGraph StateGraph checks question relevance, fetches the live schema, generates PostgreSQL, validates it with a dry run, retries on failure, executes the query, and narrates the result set in plain English. The agent uses prompt engineering only; no model was fine-tuned. We evaluated it on the Chicago Crime dataset (approximately 8.5 million records, 22 attributes) against a hand-built benchmark of 100 natural language questions with ground-truth SQL, stratified into 30 Easy, 40 Medium and 30 Hard items. Comparing two prompt revisions of the same agent, the revised system (V2) reached a Valid SQL Rate of 93% (from 87%), an Execution Accuracy of 60% under a hybrid relational equivalence metric (from 47%; 19% from 12% under strict JSON matching), and a mean Synthesis Quality of 4.34 out of 5 (from 3.91). The single largest driver was removing a LIMIT 10 instruction from the system prompt, which had been truncating multi-row answers. Error analysis attributes the residual failures to relevance-checker false rejections, ambiguous question semantics, and free-tier API rate limits rather than to the language generation step. We report no comparison against an external baseline system or a public benchmark; the study is a single-model engineering evaluation."
    }
]