back_office_ops · saas · workflow
LinkedIn SQL Bot: practical text-to-SQL for self-service data analytics at scale
Data experts at LinkedIn spent a significant amount of their time helping colleagues find data, creating a bottleneck that frustrated data teams and delayed crucial insights for business partners.
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
A user submits a natural language question to SQL Bot within the DARWIN data science platform.
Tools used
SQL BotDARWINLangChainLangGraphDataHub
Outcome
SQL Bot is now utilized by hundreds of employees across LinkedIn's business verticals; in a recent survey ~95% rated query accuracy as 'Passes' or above, and adoption increased 5-10x after integration into DARWIN.
Results
Volume5-10x
Grounding & classification
Source type: technical build writeup
29 fields verified against source quotes.
conversational aidata extractionenterprise searchmulti agent workflowragknowledge basebuilder submittedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareaccuracy improvementemployee productivitytechnical build writeupback office opsagentic task executionrag answering