Deep dive — chart 1

Chart 1 — rolling mean triage-score by client segment

The chart your Managing Partner and General Counsel should look at first. Where the silent segment divergence begins, in one visual.

7-day rolling mean case-intake triage score per client segment over 90 days

7-day rolling mean case-intake triage score per client segment over the 90-day audit period. Multi-segment divergence begins Day 30 and never recovers.

What you are looking at

X-axis: Day 1 through Day 90 of the audit period
Y-axis: 7-day rolling mean of the AI's triage score (0-100 scale)
Each line: one client segment (C1 = young low-income, C2 = young-to-mid upper-middle, C3 = age 40-55 mid-income, C4 = age 55-70 mixed, C5 = age 70+ fixed-income)
Baseline window: the first 30 days establishes what "normal" looks like per segment

What the eye sees

The segment lines start clustered during the baseline window. From Day 30 forward, they begin to separate. By Day 51, several segments (C1, C4, C5) show clear divergence from baseline. By Day 86, C3 has joined them — and its lane-rate shift into SIU/fraud-review will be the finding with the sharpest legal bite.

This is the pattern an experienced intake supervisor instinctively recognizes: something in the intake stream changed, and the AI is scoring segments differently than it did at baseline. The 53 percentage-point C3 lane-rate shift is the operational follow-on.

What the sensor fires on

The sensor is not looking at the eye's pattern. It is running four quantitative thresholds against each 7-day window per client segment:

Mean-shift: is the 7-day mean > 1.5 standard deviations from baseline mean?
Variance-ratio: is the 7-day variance > 1.5x baseline variance?
KL-divergence: is the shape divergence between baseline and current distribution > 0.2?
Segment-differential: is the max cross-segment shift > 12%?

Day 51 fires C5 KL-divergence 2.25 (10x the threshold). Day 79 fires C5 again at 0.96. Day 86 fires C4 at 0.80. The pattern the eye sees is the pattern the sensor quantifies.

What defense counsel + carriers care about

Defense counsel does not read charts — they read attestations. But when an attestation is challenged, the chart is the exhibit. FRCP 37(e) motion briefs, malpractice-carrier post-claim review, state bar disciplinary counsel intake teams, and plaintiff-class experts all understand the "one client segment moves silently" pattern instantly.

The chart also tells the counterfactual story: had this monitoring been in place operationally, the drift window would have been ~7-14 days rather than 45+.

The next chart

The rolling-mean chart shows when. The baseline-vs-drifted chart shows how the C3 distribution shape shifted.

Chart 2 — baseline vs recent distribution →

$499 Snapshot. 3 business days.

Same 3-chart set for your firm's actual AI surface + full analysis report.

Buy $499

Back to legal sample hub.