Search cases, suites, agents…⌘K
DEMO · synthetic data
Live/windows/2026-w25

2026-W25 · daily

Jun 15 – 21 · online run — an evidence packet satisfying EU AI Act Art. 72 post-market monitoring, and it flows into the Governance ledger.

Watch window — HEALTHY
All five rollups inside their bars this window.
190
traces
5
rollups
healthy
verdict

Pinned

everything this online run scored against
2026-W25 · daily
window
2026-W25 · dailyJun 15 – 21
scope
portfolio sample — hr-policy-advisor + payroll-copilot (the two judge-covered agents this window)
sample
190 traces sampled — 120 via Phoenix · 70 via Langfuse
guardrail config
guard-pack@prod-2026.06 — in sync with offline safety@v2
agent build
hr-policy-advisor 1.8.1 · prompt v14 · payroll-copilot 0.9.3 · prompt v10 — both unchanged through the arc below
Same pinning discipline as a sealed run — window, sample, judge versions, and guardrail config are all versioned, auditable assets (§57).

Score scoreboard

native units, per concern — never blended
ConcernMetricResultBarVerdict
Retrievalgroundedness
0.91
≥ 0.90pass
Safety / PIIpii incidents shipped
0
= 0pass
Numericoracle corrections
2.4/day avg
alert ≥ 5/daypass
Functionalonline-eval pass rate
93%
≥ 90%pass
Safety / PIIrefusal correctness
0.96
≥ 0.95pass
Native units by design (§12) — 0.93 groundedness, 0 pii incidents, "3 today" oracle corrections. Flattening these to one score is how a breach hides.

Groundedness trend

vs the hr-policy-release-gate bar, across recent windows
bar 0.902026-W25 · groundedness 0.91 · pass2026-W250.912026-W26 · groundedness 0.88 · fail2026-W260.882026-W27 · groundedness 0.85 · fail2026-W270.852026-W28 · groundedness 0.93 · pass2026-W280.93
W26 and W27 fell below the bar two windows running — that sustained pattern, not either window alone, is what triggers the alert (§58).
Representative traces from this window feed the trace inbox via the same four feeds as the activity stream — guardrail, online-eval, drift, and end-user feedback.