sanitized source model
Back to proof
AI-Assisted Basketball Scheduling Decision Workflow
A staff-facing basketball scheduling workflow that turns messy NCAA data and selection-committee constraints into repeatable decision support.
Synthetic public view Scheduling decision loop
Raw ratings
Committee constraints
Scenario compare
Staff brief
NET/RPI inputsQuadrant checksDecision memo
quadrants and tradeoffs
decision-ready summary
Recruiter answer
What proof does this case study show?
This case study shows AI implementation ability through workflow scoping, decision-support design, data validation, scenario comparison, and operator-ready briefing output.
Role fit
- AI workflow implementation
- Decision-support enablement
- Operator-facing analytics adoption
Validation signals
- Source checks before recommendation
- Scenario comparison instead of one-shot output
- Human review before staff use
Problem
Schedule planning was high stakes, data-heavy, and difficult to translate into repeatable staff decisions quickly.
What I Designed
Defined the scheduling problem, success criteria, data checks, briefing format, and adoption loop, then used AI coding assistance to help build and harden the dashboards and scripts.
Validation
Used scenario comparison, quadrant classification, source checks, and concise brief outputs so operators could review the recommendation instead of trusting a black box.
Public Handling
The public version uses synthetic visuals and avoids internal strategy, private data, and claims of sole engineering ownership.
Synthetic artifacts
What the public proof can show safely.
These artifacts describe the workflow shape without exposing private data, credentials, logs, internal strategy, or real customer/user records.
Ratings inputs -> constraints -> scenario comparison -> staff decision brief.
Synthetic opponent options with tradeoffs, quadrant impact, and decision notes.
Quadrant classification, source consistency, and human review before use.
No internal strategy, private data, or claims of sole engineering ownership.
Positioning note
This work is framed as AI-assisted implementation. My ownership is problem definition, workflow design, evaluation criteria, validation, rollout, user feedback, and adoption. Coding-heavy pieces were built with AI coding assistance.
Good fit for teams that need someone to turn high-stakes, messy operating decisions into AI-assisted workflows people can review and adopt.