back_office_ops · finance · workflow
Ramp Research: In-house AI analyst agent answers 1,800+ data questions per month in Slack
Data questions at Ramp stacked up behind a single on-call analyst in a #help-data Slack channel, causing decisions to wait hours for answers and leading most questions to go unasked entirely as people hesitated to add to the queue.
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 · Data question asked in Slack
Users ask data questions directly in Slack, 24/7, in the #ramp-research-beta channel.
Tools used
SlackLookerSnowflakedbtRedashPython
Outcome
Ramp Research answered over 1,800 data questions across 1,200+ conversations with 300 different users and caused a 10-20x increase in questions asked — with 1,476 answered in the beta channel over 4 weeks versus 66 in the old #help-data channel.
What failed first
An initial human-in-the-loop system that pinged domain owners for every in-domain question didn't scale because effort still grew with request volume, reintroducing the core bottleneck.
Results
Time saved1,476
Volumeover 1,800
Running sinceearly August
Grounding & classification
Source type: technical build writeup
38 fields verified against source quotes.
agentic workflowai agentdata extractionenterprise searchragknowledge basebuilder submittedfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedfinancial servicessoftwarecycle time reductionemployee productivityresponse time reductionthroughput increasetechnical build writeupback office opsfinance opsagentic task executionrag answering