Predictability risk rising in 1st-down personnel groupings
Pending:51 CRITICAL
Conflicts:3
Confidence:84%
flyiQ
Loading...
Ask AI
No game selected
Source-grounded answers
Welcome to FlyIQ Ask AI. I can help you analyze game film, find specific plays, generate reports, and identify coaching opportunities.
Try asking me to:
- Find clips matching specific criteria
- Generate teach tape for a player or position group
- Build a scouting or post-game report
- Identify the top fixable errors from any game
All answers are source-grounded in your actual game data and evaluation pipeline.
04:01 AM
Quick actions
AI responses are grounded in your game evaluation data
Play Review
Play 14 - PA Boot RT
Flagged
C-
72/10058%Low
Model evaluation score and confidence
Model Claim
Offensive line failed to execute zone blocking scheme, resulting in immediate pressure from the defensive end. The quarterback was forced to throw off-platform, leading to an inaccurate pass.
OL_ZONE_BLOCK_001
Left tackle failed to reach the defensive end on the zone step
OL_COMBO_BLOCK_003
Guard-tackle combo did not transfer cleanly to second level
QB_POCKET_002
Quarterback climbed pocket when edge was still available
WR_ROUTE_DEPTH_001
Routes reached correct depth for play-action concept
Which input features contributed most to this grade?
Decision Attribution
Breakdown of the DECISION grade (78) into sub-factors.
Pre-snap Read89
Excellent identification of Cover 3 rotation
Progression84
Correct read order: 1 → 2 → checkdown
Patience76
Slightly early — could have let route develop 0.3s more
Risk Assessment82
Acceptable risk given down/distance context
Counterfactual Analysis
"What if" — projected grades for alternate decision paths.
Actual throw (Read 1: McMillan)
14 yd gain, 1st down
78
—
Thrown to Read 2 (Mitchell underneath)
Projected 6 yd, short of sticks
71
-7
Thrown to Read 3 (Whittington corner)
Tight coverage, PBU likely
64
-14
Checkdown to Baxter
Projected 3 yd, 4th down
58
-20
Tuck and scramble
Edge pressure, loss projected
49
-29
Confidence Breakdown
Engine confidence per grade axis — 95% CI error bars.
DEC78
CI: [72, 84] · ±6
TCH84
CI: [80, 88] · ±4
OUT88
CI: [85, 91] · ±3
EFF82
CI: [77, 87] · ±5
Validation Trail
✓
Cross-checked against ESPN play-by-play
Yardage, player, outcome match
PASS
✓
Cross-checked against EPA model
EPA delta +1.24 aligns with grade 83
PASS
✓
Formation classification consensus
11 personnel · 3-wide trips right
PASS
✓
Coverage classification consensus
Cover 3 · MOFC · curl-flat weak
PASS
✓
Engine bulletproof check (v8.2.0)
No drift, no anomalies
PASS
VALIDATION STATUS: VERIFIED · 5/5 checks passed
Similar Plays
5 most similar plays in dataset (by feature vector cosine distance)
TEX-2025-W6-P0142Ewers 3rd & 6 slant to Worthy81
ORE-2025-W4-P0283Gabriel 3rd & 8 in-breaker to Johnson79
LSU-2025-W9-P0411Nuss 3rd & 7 dig to Thomas85
UGA-2024-W11-P0198Beck 3rd & 7 curl to McConkey76
OSU-2025-W3-P0356Howard 3rd & 7 slant to Egbuka82
Coach Translation
PLAIN ENGLISH
QB made the right read but threw a beat early. Receiver made up for it with a catch outside his frame. Result was good but the process had a small flaw — decision grade docked for throwing before the route fully developed. Coach him on patience in the pocket against Cover 3 rotation; the rest of this rep is a teachable positive.
Trust Layer
Validation Confidence
96.4%
5/5 cross-checks
Sample Size
2,847
similar reps trained
Engine Version
v8.2.0
bulletproof framework
Calibration Δ
+1.2
vs EPA-implied grade
Coach Agreement
87%
on review (14d window)
Drift Score
0.04
well within tolerance
This play is part of a broader trust system: every grade is triangulated against ESPN PBP, the EPA calibration engine, and coach review overrides. Grades that drift from expected distributions are auto-flagged into the review queue. Confirmed corrections train the model — flags alone do not. Engine health: GREEN.