Who should use the SQL Generation workflow?
Teams or solo builders working on data tasks who want a repeatable process instead of one-off tool experiments.
Execution Map
7-step pipeline — follow each step in order
1Setup · Step 1 of 7
Open task pageGenerate SQL queries
Prepare inputs and settings through Generate SQL queries before running sql generation.
Why this matters
Generate SQL queries sets up the foundation for sql generation; clean inputs here reduce downstream rework.
What you get
Inputs, context, and settings are ready so the workflow can move into execution without blockers.
2Input · Step 2 of 7
Open task pageText-to-SQL
Use Text-to-SQL to build supporting assets that improve sql generation quality.
Why this matters
Text-to-SQL strengthens sql generation by feeding better supporting material into the pipeline.
What you get
Supporting assets from text-to-sql are prepared and connected to the main workflow.
More optionsCompare
3Input · Step 3 of 7
Open task pageSynthetic Data Generation
Use Synthetic Data Generation to build supporting assets that improve sql generation quality.
Why this matters
Synthetic Data Generation strengthens sql generation by feeding better supporting material into the pipeline.
What you get
Supporting assets from synthetic data generation are prepared and connected to the main workflow.
More optionsCompare
4Core · Step 4 of 7
Open task pageSQL Generation
Execute sql generation with SQL Generation to produce the primary decision-ready insight.
Why this matters
This is the core step where sql generation actually happens, so it determines baseline quality for everything after it.
What you get
A first-pass decision-ready insight is generated and ready for refinement in the next steps.
More options
5Refine · Step 5 of 7
Open task pagePerform SQL queries on unstructured data
Refine and validate sql generation output using Perform SQL queries on unstructured data before final delivery.
Why this matters
Perform SQL queries on unstructured data adds quality control so issues are caught before the workflow is finalized.
What you get
The decision-ready insight is improved, validated, and prepared for final delivery.
6Refine · Step 6 of 7
Open task pageHallucination Detection (e.g., Lynx), Financial Data Benchmarking (e.g., FinanceBench), Reasoning Chain Generation (e.g., GLIDER)
Refine and validate sql generation output using Hallucination Detection (e.g., Lynx), Financial Data Benchmarking (e.g., FinanceBench), Reasoning Chain Generation (e.g., GLIDER) before final delivery.
Why this matters
Hallucination Detection (e.g., Lynx), Financial Data Benchmarking (e.g., FinanceBench), Reasoning Chain Generation (e.g., GLIDER) adds quality control so issues are caught before the workflow is finalized.
What you get
The decision-ready insight is improved, validated, and prepared for final delivery.
7Deliver · Step 7 of 7
Open task pageSQL/Python scripting
Package and ship the output through SQL/Python scripting so sql generation reaches end users.
Why this matters
SQL/Python scripting is what turns intermediate output into a usable, publishable result for real users.
What you get
A finalized decision-ready insight is ready for publishing, handoff, or integration.