What inputs does the Natural Language SQL workflow use?

The workflow uses Question, Database, Output Format. Required fields and their expected formats are listed on this page.

What resources are included in the Natural Language SQL blueprint?

The blueprint contains 2 AI agents, 0 functions, 1 MCP server. Its workflow pattern is Dag.

All blueprints Data & Analytics AI workflow blueprint

Natural language to SQL workflow blueprint

Type a question, get a validated SQL query and formatted results

See where this blueprint fits in the production workflow lifecycle

Data

SQL

Reports

Analytics

Request access

Pattern

Dag

Agents

2

Functions

0

MCP servers

1

Inputs for the Natural Language SQL workflow

Provide the following information when starting this workflow. Required inputs are validated before the first workflow stage runs.

Question
Required
Business question (e.g. "What were top 10 products by revenue last quarter?")
Type: String
Database
Required
Target database name (e.g. analytics_prod)
Type: String
Output Format
Optional
Report format: table, summary, or detailed
Type: String

Input template

This request shape is generated from the blueprint's input schema. Angle-bracket values are placeholders; defaults and examples appear only when the source blueprint defines them.

{
  "question": "<required string>",
  "database": "<required string>",
  "output_format": "<optional string>"
}

How the Natural Language SQL AI workflow works

This data & analytics blueprint uses a dag workflow with 2 agents, 0 functions, and 1 MCP server. This catalog blueprint is available by request; contact GraphN to discuss access and customization for your use case.

Report Loop
Judge Loop

Blueprint resources and prerequisites

These are the actual agents, functions, and MCP servers declared by the blueprint. If an MCP server connects to an external system, configure the required connection and credentials in your GraphN workspace before running the workflow.

AI agent

Report Writer

You are a data analyst who writes SQL reports from natural language questions.

AI agent

Data Auditor

You are a data quality auditor.

MCP server

Database Tools

Database query and schema inspection tools

Tools: Get Schema, Run Query, Validate Sql

Workflow output contract

The completed workflow makes the following output available to downstream steps, applications, or API clients:

Report Loop

Frequently asked questions

What does the Natural Language SQL blueprint do?: Type a question, get a validated SQL query and formatted results
What inputs does the Natural Language SQL workflow use?: The workflow uses Question, Database, Output Format. Required fields and their expected formats are listed on this page.
What resources are included in the Natural Language SQL blueprint?: The blueprint contains 2 AI agents, 0 functions, 1 MCP server. Its workflow pattern is Dag.
Can I customize the Natural Language SQL blueprint in GraphN?: This blueprint is currently available by request. Contact GraphN to discuss access and customization for your use case.

Related Data & Analytics blueprints

View all data & analytics workflows

Video Analysis

Analyze stored videos using sampled key frames and best-effort speech transcription

Anomaly Detector

Monitor metrics and generate readable alerts when anomalies occur

CSV Analyzer

Upload any CSV file and get automatic profiling, chart descriptions, and key insights

Dashboard Narrative Writer

Connect your dashboard metrics and get a weekly narrative explaining what changed and why