BlackPrint Technologies · Jul 2026
Expansion Intelligence OS
AI-Operated Retail Expansion Planning
Overview
Built an AI-operated expansion operating system, deployed as executive demos for two national retail chains and a global quick-service restaurant brand, that takes expansion teams from territorial analysis to site evaluation, deterministic monthly financials and a five-year opening plan.
Highlights
- 01
Built a dual-brain AI analyst: Claude tool-calling over deterministic services with an intent-router fallback for when the live model is unavailable, driving the map through a typed visual-action bus (87% prompt-cache hit rate).
- 02
Engineered a deterministic monthly financial engine calibrated to public disclosures within +0.27% on published sales productivity, feeding site evaluation, scenarios and a five-year plan.
- 03
Integrated warehouse data through a read-only ETL (184 road-network isochrones, 19 DENUE editions, a 4,894-cell H3 demand layer) and adapted the financial engine from grocery retail to quick-service formats, with 235–286 automated tests per deployment.
Stack
- Next.js 16
- React 19
- TypeScript
- Vercel AI SDK
- Anthropic Claude
- MapLibre GL JS
- Turf.js
- H3
- Zustand
- Zod
- Deterministic Financial Modeling
- Vitest
Working on something similar?
Tell me about the problem and the data behind it. I reply within 24–48 hours.
Discuss a project