Deep dive — chart 3

Chart 3 — lane rate per client segment, baseline vs recent

The chart with the operational + legal bite. Where score-distribution shifts translate into actual intake routing. C3 SIU/fraud-review rate rose 18% to 71%. Other segments stable. That is the exact adverse-impact signature the four-fifths test flags.

Triage-lane rate per client segment, baseline vs recent

Triage-lane rate per client segment — baseline (left) vs recent (right). C3 SIU/fraud-review rate rose sharply while other segments stayed stable.

What you are looking at

Grouped bars per client segment (C1 / C2 / C3 / C4 / C5)
Three colors per segment: Fast-Track Settle (green) / Standard Adjuster Review (blue) / SIU / Fraud Review (red)
Left cluster: baseline (first 30 days) — the "normal" routing per segment
Right cluster: recent (last 30 days) — the current routing per segment

What the chart shows

C1, C2, C4, C5 — lane rates roughly stable between baseline and recent.
C3 — SIU/fraud-review rate rises sharply (18% baseline → 71% recent). Standard Adjuster Review rate shrinks. Fast-Track Settle drops toward zero.
The differential exists only for C3. Other segments are unaffected.

53 percentage-point differential in SIU/fraud-review lane routing. One client segment. Silently. Over 45+ days. Under the four-fifths test used for adverse-impact analysis, a C3 SIU-review rate 5-15x other segments' rates is a clear-cut prima facie showing.

Why aggregate metrics missed it

Because C3 is one segment among five, the aggregate SIU/fraud-review lane count barely moved: the C3 rise rounded to noise across the whole intake volume. That is why the case-management dashboard stayed green. Aggregate metrics are inherently blind to segment-differential patterns, and segment-differential patterns are inherently what adverse-impact analysis is built to surface.

The signal that fired the A/B/C determination

Multi-segment high-severity divergence — 7 high-severity events across C1, C4, and C5 by Day 51, plus C3's own shape shift landing Day 86. Once high-severity count ≥ 3, the Snapshot lands on Category C by rule — no matter what any other metric shows.

See the Category-A/B/C decision logic →

The exhibit-quality read

This chart is what a plaintiff-class expert or defense counsel asks the firm for first in an adverse-impact matter. It is also what the firm's GC should have on file before either lands — because the same chart, in the firm's hand, tells a different story:

Same chart, operator stance: "we identified this pattern through independent verification on Day X, initiated the following remediation on Day X+N, and here is the timeline of that remediation." The chart becomes evidence of good-faith investigation, not evidence of missed monitoring.

$499 Snapshot. 3 business days.

Same lane-shift chart for your firm's actual AI surface + full determination + 3 fix-first items.

Buy $499

Back to legal sample hub.