finance_ops · finance · workflow

NYSE/ICE builds a structured RAG text-to-SQL system on Databricks Mosaic AI with 96% execution accuracy in five weeks

ICE business users had no way to query structured financial data without understanding data models, SQL schemas, or writing SQL queries, creating a barrier to self-service analytics.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User submits natural language question
When a question is submitted, an embedding vector is created and matched against the vector indexes.
Tools used
Unity CatalogVector SearchFoundation Model APIsModel ServingInference TablesAgent Bricks AI GatewayLlama3.1-70BMLflowGitHubSpider
Outcome

In five weeks, the team built a text-to-SQL system achieving 77% syntactic accuracy and 96% execution matches, enabling non-technical business users to query structured financial data in natural language.

Results
Time savedfive weeks
Volume77%
Source

https://www.databricks.com/blog/unlocking-financial-insights-nyse-ice

How we source this →

Grounding & classification
Source type: technical build writeup
30 fields verified against source quotes.
data extractionknowledge searchragknowledge basehuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedfinancial servicesaccuracy improvementemployee productivitytechnical build writeupback office opsfinance opsrag answering