Jun 2026
Why most procurement dashboards lie quietly
On the gap between what a Power BI tile shows and what a buyer actually decides at 7:42 AM on a Tuesday.
Read note →Vol. I · Decision Systems Lab
Building the Future of
Human Decision Making.
I design intelligent systems that help people make better operational decisions. A working notebook at the intersection of AI, operations research, analytics, and human judgment.
01
Discipline
Operations Research
02
Method
Systems Engineering
03
Medium
AI + Analytics
04
Aim
Human Judgment
Mission
Most operational decisions are still made on intuition, scattered spreadsheets, and yesterday's data. I build the decision systems that change that: engines that fuse AI, optimization, and the texture of human expertise into one calm interface.
AI
Models that learn from operational reality, not just clean training data.OPERATIONS RESEARCH
Optimization and simulation as the spine, not the marketing.Judgment
Interfaces that respect the expert on the other side of the screen.Featured System · 001
Procurement
Heat Map Engine.
An automated inventory planning and decision support system. It fuses SAP data, PowerShell automation, Excel calculation logic, and Power BI dashboards into one daily ritual that tells a planner exactly where attention is needed.
SAPPowerShellExcelPower BIDecision Engine
Open the case study →Fig. 001 · System architecture
Portfolio
Systems I'm building.
- 001Procurement Heat Map EngineShipped · In ProductionAutomated inventory planning that surfaces only the SKUs that need a human decision today.→
- 002Site Financial Health EngineIn DevelopmentAutomated finance decision engine connecting P&L data, GL account detail, cost center actuals, and plan data into a unified Power BI dashboard.→
- 003Qualitative Intelligence EnginePrototypeLLM powered system that converts qualitative inputs into structured, measurable insights.→
Open Questions
Questions I'm exploring.
These are the prompts that organize the work. They aren't rhetorical, each one has a research thread.
- Q01
How do we design AI that augments operational judgment rather than replacing it?
- Q02
What does optimization look like when the objective function is contested by humans in the loop?
- Q03
Can a decision log become the training set for the next generation of internal AI?
- Q04
Where does deterministic logic end and probabilistic reasoning begin in supply chains?
- Q05
How do we build systems that are calm by default and loud only when it matters?
Journal
Field notes.
May 2026
PowerShell as a decision engine runtime
Notes on why a 'scripting language' became the most reliable orchestration layer in our planning stack.
Read note →Apr 2026
On heat maps as moral objects
Color is an argument. Choosing the gradient is choosing whose pain is visible first.
Read note →