MOI parses email threads plus PDF and Excel attachments, extracts RFQ fields, then supports code mapping, human validation, and SQL Server ingestion.
Requests arrived as forwarded EML chains with line items spread across scanned PDFs, Excel tables, and signature content, making clean system entry difficult.
Rules reconstruct the email chain and identify the internal salesperson; visual and table processing clean attachments, and a JSON Schema guides extraction of 10 key fields. Tables over 100 rows are batched and merged.
Exact and semantic part matching plus condition-code mapping prepare reviewed Header and Line records for transactional SQL Server writeback and downstream natural-language analysis.