Parametric price benchmarking for engineering and procurement trade-offs. Agentic first, runs on your data, stays on your machine.
Should-cost BoQ benchmarking for Singapore and India: SMM2 / IS 1200 classification, a rate library derived from published schedules of rates, CPI or PPI index bridging, and variance, waterfall and sensitivity reporting. FastAPI + React. MIT code, CC BY 4.0 data.
This portfolio demonstrates hands-on experience in capital equipment program management and strategic supply chain operations within advanced manufacturing environments
Hardware procurement and asset-lifecycle SCM, demoed as a Device-as-a-Service fleet: buy, rent for 12 to 48 months, take back, refurbish, re-rent, resell. Should-cost, TCO per rental cycle, and an LLM that advises while deterministic code decides, held by a 29-scenario agent-safety harness. Live demo plus analytics cockpit.
End-to-end commodity analytics for 2nd-tier metals (Cu, Al, steel). Python pipeline + Power BI: should-cost vs. invoiced price, €6.1M cost-at-risk on expiring contracts, and Tier-2 entity resolution that reveals a hidden single-source smelter. Synthetic data.
What an EV battery cell should cost to make, recomputed monthly from IMF metal prices: chemistry-derived bill of materials, cost attribution, price risk, and exposure by automaker.
To associate your repository with the should-cost topic, visit your repo's landing page and select "manage topics."