Ricoh builds a scalable intelligent document processing platform on AWS for healthcare clients
Ricoh's healthcare document processing relied on bespoke engineering per customer, with each deployment requiring unique development, custom prompt engineering, model fine-tuning, and integration testing that could not be reused—consuming 40–60 hours of developer time per customer setup. With an anticipated sevenfold increase in document volume, these bottlenecks limited expansion. Strict compliance requirements (HITRUST, HIPAA, SOC 2) further constrained AI innovation.
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 · Document ingestion via S3
Healthcare documents enter the system through Amazon S3, triggering event-driven processing workflows.
Ricoh reduced customer onboarding time by over 90% (from 4–6 weeks to 2–3 days) and cut engineering hours per deployment by over 90% (from ~80 hours to under 5 hours). Monthly throughput is projected to grow sevenfold to over 70,000 documents. The solution achieves 98–99% extraction accuracy while reducing manual review costs by 60–70% compared to fully manual processing, with annual savings exceeding 1,900 person-hours.
What failed first
A simple API call to Amazon Bedrock—sending a scanned document alongside a prompt—was insufficient for complex multi-part healthcare documents. Template-based extraction also proved ineffective given the high variability in layouts, naming conventions, and document structures across healthcare providers.