it_support · finance · workflow
Nubank builds RAG-based internal knowledge search on Slack to reduce support tickets
Nubank's ~9,000 employees were spending significant time navigating fragmented per-team Confluence documentation and frequently opened support tickets just to find the right information or identify which team owned a topic.
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 · Employee query via Slack
Employees submit information queries through the Slack-integrated tool.
Tools used
LLMRAG
Outcome
The tool was adopted by most Nubankers, reducing both the time employees spend finding information and the number of support tickets created; the router achieves 78% precision and 77% recall, and 74% of internal domain answers were labeled accurate by department owners.
Results
Time savedreducing the amount of time to find the information they need
Volume78%
Grounding & classification
Source type: technical build writeup
25 fields verified against source quotes.
document classificationenterprise searchknowledge searchragknowledge basehuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedbankingaccuracy improvementdeflection ratetime savedtechnical build writeupback office opsit supportextract classify routerag answering