Memo Risk & Sales Intelligence.
JAS Diamonds, a Chicago wholesale diamond business, sells on memo: a retailer takes a stone, tries to sell it, and pays or returns it later. About 2,130 open memos worth over $20M sat in a legacy ERP with no API. 3Pillars built a sales and risk intelligence layer on top of it, with Claude in the product and Claude Code behind the build.
Company Profile
JAS Diamonds is a family-owned wholesale diamond business in downtown Chicago, founded in 1983, that grows, imports, manufactures and sells mined and lab-grown diamonds to retailers. Sixteen sales reps work the memo book. The ERP is a legacy, vendor-hosted system with no API; the CRM had been adopted but never maintained.
The Challenge
The business had no reliable way to track its memo book. Reps worked from memory and instinct. Nobody knew which memo was old, which account was slow to pay, or which retailer to call next. Follow-up was manual email, written one at a time. Credit risk lived in a third-party report nobody cross-checked. After months on a mainstream CRM, fewer than 1 in 2,000 company records had a valid owner, so it showed the wrong picture and nobody trusted it.
$2M sat past due across 234 accounts, with over $20M of inventory on consignment and out of sight. Reps spent the first hour of each day deciding who to call with no data behind the choice. Memo status chases took days of staff time each week. Slow-pay accounts aged silently until the stone was gone or the balance was stale.
The memo book kept growing and past-due balances reached critical levels. The firm knew its data could answer these questions but had no way to reach it.
What 3Pillars Built
An API over an ERP with no API
The ERP’s internal data reverse-engineered into a versioned, 28-endpoint service, with a data store behind it.
Memo risk scoring
Every open memo rated 0 to 100 every 15 minutes on age, value and Jewelers Board of Trade credit data.
Follow-up engine
Status requests for aged memos and past-due invoices drafted in batches; a staff member approves each batch before anything sends. Gmail send and inbound reply detection; HubSpot contact and owner sync.
Sales workbench
Each of 16 reps opens the day with a ranked 15-call queue and full account context pre-assembled.
Claude assistant
A natural-language assistant on Claude answers sales, margin, memo and inventory questions and exports spreadsheets.
Staff querying live data in Claude
A read-only MCP server with query allowlists, scrubbed credentials and per-user audit logs lets the client’s own claude.ai accounts query the database; an Agent Skill teaches Claude the schema.
Daily RapNet market prices (about 283,000 listings) feed buying intelligence, and a nightly sync keeps about 6,300 CRM customer records aligned with the ERP. A 181-test automated suite guards the follow-up engine and runs before every deploy. The client’s team now sees the whole memo book, ranked by risk, every morning.
Results
Faster collection on even 1% of past-due balances offsets the platform’s full annual cost. Figures come from the platform’s own databases and sync audits, April to August 2026.
Functional Areas Touched
Highlighted nodes are where the platform changed daily work.