LO
DeploymentCognitive automation2024-12-09
LinkedIn deployed a text-to-SQL assistant used by hundreds of employees across its business verticals, saying data experts had spent much of their time helping colleagues find data
Business systems owneroccupation page →
Event date / reported
2024-12-09
Evidence stage
DeploymentAn employer has put it into production. Can move the baseline — weighted by scale and how similar the setting is.
Tasks this bears on
Making the numbers mean something
Building the reports management steers by, and being the one who knows which of those numbers is solid and which is held together by an assumption.
Automating✓ Evidence-backed
Where this applies
LinkedIn's engineers describing an internal tool, SQL Bot, which the company does not sell. They say data experts spend a significant amount of their time helping colleagues find data they need, delaying business partners; that SQL Bot is now used by hundreds of employees across LinkedIn's business verticals, with sustained adoption after it was integrated into the company's data-science notebook platform; that it only became usable after domain experts identified key tables in their areas and wrote mandatory table descriptions; and that in a survey about 95% rated its query accuracy "Passes" or above and about 40% "Very Good" or "Excellent". Adoption and accuracy are self-reported; users include analysts as well as business staff.
What this means
The queue of 'can you pull this number for me' is exactly what plain-language querying removes, and a large company says it has done so for hundreds of staff. The work that remained was deciding which tables are authoritative and what they mean — done by people, and made mandatory.
What it does not yet show
One company's internal tool with self-reported adoption and accuracy; it does not show who catches a confidently wrong number, or whether any role shrank.
What you can check
Open LinkedIn Engineering's "Practical text-to-SQL for data analytics" and find "now utilized by hundreds of employees across LinkedIn’s diverse business verticals".
Does it change the assessment?
No. The impact index is never moved by a single event. What this record did: the 1 linked task judgement above now rest on evidence instead of inference.
Source
LinkedIn Engineering blog — Albert Chen et al., "Practical text-to-SQL for data analytics" (9 December 2024) · verified 2026-09-28 · Claude (VOLO agent) · interpreted 2026-09-28 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.