ChemMasters Data Platform
AI-powered data platform for a chemicals company
Project Summary
Production AI platform for a chemicals distributor — two integrated halves. (1) Email automation: a Celery Beat dispatcher polls inbound mail every 60s, acquires PG advisory locks per email for crash-safe mutual exclusion, hands off to a Unified Email Agent (Claude) that classifies, extracts, and routes; a companion Email Response Agent drafts replies. A truth-set eval harness keyed by Sage OR# regression-tests every Claude prompt change against curated real-world cases before promotion. (2) Data platform: unifies legacy Sage product/customer data with semantic search (Vertex AI Search), AI trip-report generation, and a document pipeline that extracts SDS/TDS PDFs via GCP Document AI. MCP server and REST APIs expose the unified data to AI agents and a Slack/React surface.
Our role: Architecture & Engineering
What We Did
- Crash-safe email pipeline using PG advisory locks for per-email mutual exclusion
- Unified Email Agent (Claude) classifies, extracts, and routes inbound mail end-to-end
- Companion Email Response Agent drafts replies for human review
- Truth-set evaluation harness keyed by Sage OR# regression-tests every prompt change before promotion
- Unified data from legacy Sage system with modern AI-powered semantic search
- Automated SDS/TDS document classification and extraction via GCP Document AI
- AI trip report generation saving hours of manual data entry per rep
- MCP server enabling AI agents to query product and customer data
Want something like this?
Describe what you'd build and get a scoped plan with a budget — drafted in minutes, confirmed by a human.
Scope Your Project — Free