EDGE3 Football · Recruiting Decision Intelligence for NCAA Staffs

The board condenses up the chain.

47 prospects → 8 shortlisted → 2 finalists. One model. Three lenses. Click a tab below to see what each role sees.

Analyst

47 prospects · 22 metrics

Builds the board

Position Coach

8 cards · scheme + behavior

Narrows to film-worthy

Head Coach

2 finalists · R/Y/G grade

Final call

Player names + model scores in the tabs below are real (FB Combined R/Y/G v1, 2025 forward predictions). Scheme flags + position-coach narratives are illustrative pending live Coach Suite onboarding.

Portal QB board: building the shortlist

Analyst view

Build the board. Share with the QB coach.

Filters: Position: QB Eligibility: 2+ years Min stars: 3 Scheme fit: pro-style Risk: All Showing 8 of 47 candidates

Player	Stars	247	Roster Retention Risk Roster Retention Risk (RRR): the model’s read on how likely the player is to leave your program, on a 0–100 scale. Higher = more likely to enter the portal. Updated continuously as new signals come in.	Trajectory Performance Trajectory: whether next-season production is heading Up, Stable, or Down. Built from prior-year grades, scheme context, and behavioral signals.	Scheme Fit Scheme Fit: how cleanly the player’s game maps to your system. Green = clean match. Yellow = borderline / requires adjustment. Red = mismatch.	Behavioral	Social Signal	Combined
AJ Swann LSU	4★	0.949	0.39	+0.90 Rising	0.10 Match	Coachable	Clean	0.23	+ board
Jacob Knuth Kansas St	3★	0.877	0.42	+0.90 Rising	0.05 Match	Coachable	Clean	0.26	+ board
DJ Lagway Florida	5★	0.985	0.70	+0.41 Stable	0.10 Match	Mixed	Watching	0.52	+ board
Caden Veltkamp W Kentucky	3★	0.832	1.00	-0.06 Stable	50 Borderline	Authority flag	Frustration	0.79	pass
Ryan Boe Northwestern	n/a	n/a	0.06	+0.90 Rising	0.20 Match	Coachable	Clean	0.06	+ board

Analyst flags 3 to position coach for deeper review. Veltkamp filtered off. Risk + behavioral both pointing the wrong way.

QB room shortlist: fit + behavioral read

QB Coach view

Three flagged. Scheme fit, behavioral read, can-the-player-run-our-offense.

AJ Swann

LSU · 4★

Strong fit

Transfer risk (v8)0.39

Trajectory score+0.90 Rising

Combined R/Y/GGreen / 0.23

247 composite0.949

Scheme transitionMatch (illustrative)

Survey signalpending intake

Illustrative position-coach narrative: 4-star recruit pedigree + up trajectory across our scoring layer. Strong floor based on prior-program development pattern. Behavioral + scheme-transition data populate from survey + scheme-transition signal once onboarded.

→ Recommend to HC for spring visit

Jacob Knuth

Kansas St · 3★

Strong fit

Transfer risk (v8)0.42

Trajectory score+0.90 Rising

Combined R/Y/GGreen / 0.26

247 composite0.877

Scheme transitionMatch (illustrative)

Survey signalpending intake

Illustrative position-coach narrative: Lower star tier than Swann, identical trajectory upside on our model. Developmental ceiling reads strong, exactly the profile a position coach prefers when scheme fits. Survey + film add the qualitative read.

→ Recommend to HC for spring visit

DJ Lagway

Florida · 5★

Watch

Transfer risk (v8)0.70

Trajectory score+0.41 Steady

Combined R/Y/GYellow / 0.52

247 composite0.985 (top-tier)

Scheme transitionMatch (illustrative)

Survey signalpending intake

Illustrative position-coach narrative: Top-tier recruit pedigree but mid-Yellow on transfer-risk model. The risk score reflects program churn + opportunity context, not behavioral red flags. Talent ceiling is the highest on the board, but the recruiting fight is real if our model says he's flight-risk Yellow. Hold for HC discussion.

→ Hold. Flag for HC if we don't land Swann/Knuth

QB1 finalists: your decision

Head Coach view

Two finalists. Your call.

Rank 1

AJ Swann, LSU

4★ recruit. Trajectory model says Rising (+0.90), Roster Retention Risk v8 reads 0.39 (Green), Combined 0.23. Strongest blend on the board: high recruit pedigree + rising forward trajectory + clean risk profile. Best floor. Illustrative behavioral + social signal commentary populate from survey + social listening once onboarded.

Analyst confidence

9/10

data fit

QB Coach confidence

9/10

illustrative

Social signal weight

n/a

pending intake

PROCEED: schedule official visit

Rank 2

Jacob Knuth, Kansas St

3★ recruit, identical Up trajectory (+0.90) with slightly higher Roster Retention Risk (0.42 vs Swann 0.39). Lower-star tier but same projection upside on our model. Higher developmental ceiling, lower acquisition cost. Illustrative survey + behavioral commentary populate from intake.

Analyst confidence

8/10

data + projection

QB Coach confidence

8/10

illustrative

Social signal weight

n/a

pending intake

WATCH: strong dev pick if Swann commits elsewhere

Each confidence score is the model's read. The head coach can override and re-weight. EDGE3 is decision support, not decision replacement.

Refined Positioning

How staffs actually talk about recruits, now operationalized.

One side of the table: "He’s a can’t miss." The other: "He can’t play for us." Where does he fit in our room? Who else are we bringing in? Who does he remind you of? The two questions every staff meeting opens with, answered continuously. EDGE3 has the read before the room sits down, and updates between meetings, not just at intake.

Player Comparison · Staff Language → System Output

"Who does this kid remind you of? How does he stack up in our room?"

EDGE3’s comparison engine surfaces the answer instantly.

Pulls similar archetypes from your historical roster, national player library, and your current board
Side-by-side rate comparison across performance, scheme fit, and behavioral profile
Live positional ranking against every player you’re evaluating

The comp and ranking appear the moment the analyst flags the player.

Retention + Trajectory · Where the market is broken

"If we take him, how long is he here?" "What’s the likelihood we keep him?"

EDGE3 answers that before it becomes a problem.

Continuous R / Y / G signal powered by surveys, family input, snaps, and social signals
Trajectory tier: Up / Stable / Down
Retention probability updates as the season evolves

Drift is flagged weeks before the portal, not after.

NFL front-office framework

“Every decision comes down to the full picture: on the field, off the field, and how it fits your roster.”
Mike Greenberg (paraphrased)

EDGE3 Personalized AI Recruiting Agents

Configured to surface what’s known, and what’s typically hard to access. School sites, conference media guides, recruiting boards, and public archives, consolidated into one view. Today: data and decisions, delivered in one read.

Model performance

Validated across past seasons before any read goes live.

Roster Retention Risk Accuracy 72% accuracy on past portal cycles. Players who actually transferred vs. players who stayed. Validated, not predicted.

0.718

past cycles

Trajectory Accuracy 77% accuracy on the 2024 season. The model never saw 2024 during training. Tested on outcomes that already played out.

0.770

2024 season test

Forward 2025

7,486

FBS players scored

FBS coverage

134

FBS teams scored

One use case. One live engine.

See a real EDGE3 deliverable. Then play with the live engine yourself.

Use case · Wisconsin · 39 players · 2024 roster

Program Positional Fit Scorecard

Every player on the 2024 roster graded against the program baseline and the staff-era baseline, with HS recruiting and HS competition strength layered in. Read against the next-year season outcome.

View the Wisconsin scorecard →

Live demo · play with the engine

Try the engine yourself

Search every FBS player. Compare any two side-by-side. Drag survey + social signals on a real Wisconsin QB and watch the R/Y/G signal recompute live. The same engine your staff would use, opened up for you to play with.

Search + Compare players → Watch the trajectory shift →

Go deeper

Intelligence Loop

Survey + parent + weekly snaps + social listening. The four streams that update your roster signal continuously.

Read the doc

Social Listening

What it watches (and doesn’t), how it feeds the model, what shows up on your dashboard.

Read the doc

Models

FB Roster Retention Risk v8, Performance Trajectory v1 (2024 season (never seen during training) 77/78% accuracy), Combined R/Y/G. Tested on past seasons the model never trained on.

Open model docs

Looking for the basketball version? EDGE3 Basketball →