players and prospects reviewed
Back to proof
BYU Transfer Portal Evaluation Workflow
A staff-facing evaluation workflow that turns roster criteria, player data, fit notes, and value tradeoffs into repeatable candidate briefs.
Sample Guard A Fit tier: B+
6'4" 38% 3PT 2.1 A:TO
Role fit
Secondary ballhandler who can space, defend either guard spot, and close possessions without usage creep.
Flags
Needs film check on rim pressure and late-clock creation against length.
Review complete
Film follow-up
Low-confidence price fit
active evaluation workflow
fit, flags, and recommendation
Outcome proof
Public-safe signals from the real workflow.
These are the outcome signals safe to show publicly. Internal strategy, staff notes, and private records stay out of the portfolio.
portal players, Euro prospects, and HS recruiting cycle targets
reports integrated into staff workflow during active windows
criteria adjusted by position and roster need rather than rebuilding the system
Recruiter answer
What proof does this case study show?
This case study shows AI implementation ability through criteria design, prompt/context systems, repeatable evaluation output, staff adoption, and daily operator use.
Role fit
- AI workflow implementation
- Operator-facing evaluation systems
- Adoption and enablement for non-technical teams
Validation signals
- Criteria encoded before evaluation
- Threshold checks and red flags shown in output
- Human staff review before recruiting decisions
Problem definition, workflow design, evaluation criteria, source selection, validation, rollout, user feedback, adoption, and outcome framing.
Code, app structure, scripts, UI wiring, parsing, tests, and iteration support. I stayed accountable for whether the workflow was useful and honest.
Problem
Candidate review creates more options than staff can evaluate deeply by hand, especially when fit depends on roster context, role, competition level, and value-to-fit judgment.
What I Designed
Translated BYU-specific roster criteria into structured evaluation prompts, output formats, red-flag checks, fit summaries, and value-to-fit framing.
Validation
Kept the workflow reviewable: source stats, threshold checks, role fit, competition context, and concise reasoning before any staff decision.
Adoption
The useful signal was not a demo. Staff asked for repeat reports, used the format in daily evaluation, and routed outputs into real recruiting conversations.
Artifacts and proof
What the public proof can show.
These artifacts make the workflow concrete while keeping private data, credentials, logs, internal strategy, and real customer/user records out of public view.
Fake player profile with fit tier, role notes, stat thresholds, red flags, and staff-ready recommendation.
Public-safe example of position, size, shooting, assist/turnover, competition, and value checks.
Fake daily list showing pending targets, reviewed players, low-confidence notes, and human follow-up.
Public version keeps real players, staff notes, private value specifics, and strategy private.
Positioning note
This is operator-led AI implementation proof: workflow judgment, validation, rollout thinking, adoption, and AI-assisted build support where coding is involved.
Good fit for teams that need someone to turn expert judgment into repeatable AI-assisted evaluation workflows that operators actually use.