Ramp builds in-house RAG model to migrate industry classification to NAICS codes
Ramp's industry classification depended on a homegrown taxonomy stitched together from third-party data, sales-entered data, and customer self-reporting, yielding multiple non-auditable sources of truth and preventing teams from sharing a consistent customer view.
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 · New business enters pipeline
Internal services handle embeddings for new businesses entering the classification pipeline.
Tools used
RAGLLMClickhouseKafka
Outcome
Ramp's in-house RAG model increased classification accuracy, gave the team full control over updates and tuning, helped internal teams work more cohesively, and enabled more precise communication with external partners.
What failed first
The homegrown system produced overly broad labels — classifying a hiring platform alongside law firms and dating apps under 'Professional Services' — and required complex many-to-many mappings across 100+ internal levels to translate to standard codes, making cross-team alignment and auditing impossible.