back_office_ops · finance · workflow

Ramp migrates customer industry classification to a RAG-powered NAICS system

Ramp's industry classification relied on a homegrown taxonomy stitched together from third-party data, sales-entered data, and customer self-reporting, producing multiple non-auditable sources of truth that forced many-to-many translation layers and made cross-team alignment and external partner communication difficult.

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 · Business embedding generation
Internal services handle embeddings for new businesses entering the classification pipeline.
Tools used
RAGClickhouseKafkaLLM
Outcome

Migrating to the RAG-based NAICS system increased classification accuracy and gave Ramp's teams a consistent, auditable system with full control over updates and costs, described by stakeholders as significantly upgrading data quality and understanding of customers.

What failed first

The Homegrown system had documented issues including overly broad and inconsistent categorizations, mandatory many-to-many mappings to external standards, and classifications insufficiently nuanced to satisfy compliance requirements.

Results
Volumeup to 60%
Source

https://builders.ramp.com/post/industry_classification

How we source this →

Grounding & classification
Source type: technical build writeup
26 fields verified against source quotes.
data extractiondocument classificationragknowledge basefailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedfinancial servicesaccuracy improvementemployee productivityerror reductiontechnical build writeupback office opscompliance monitoringextract classify routerag answering