Search cases, suites, agents…⌘K
DEMO · synthetic data
Operations

Performance

A fast, available agent can still be wrong — Performance watches operations; the gates and Live watch quality. Neither substitutes for the other.

Everything here is operational — latency, throughput, availability, completion. All native units, no blended score. A slow response is not a wrong one: the gates and Live decide whether an answer is correct — Performance only decides whether it arrived.

Per-agent operations

latency, throughput & availability — serving agents only

Latency, throughput & availability

native units — seconds, req/s, % (§12)
online watch windows
Agentp50p95p99Availability
Payroll Copilot
development
1.6 s2.3 s3.4 s
99.978%target 99.9%
HR Policy Advisor
pre-production
1.9 s2.7 s3.9 s
99.969%target 99.9%
WFM Assistant
production
1.2 s1.8 s2.6 s
99.981%target 99.95%
People Navigator
production
0.5 s0.9 s1.4 s
99.995%target 99.95%
Percentiles and throughput are read off the same runs the gates use (§11); availability is measured over the quarter. Skills fold under their host agent — the serving fleet is the four agents above. Per-interaction cost for these agents lives on Cost.

Request completion & error taxonomy

counts over a stated window — guardrail blocks are working-as-intended, not errors
Payroll Copilot30-day · 152k requests
99.86%completion rate
timeout
71
5xx
44
tool failure
96
guardrail blocks240working as intended — not an error
HR Policy Advisor30-day · 410k requests
99.90%completion rate
timeout
150
5xx
90
tool failure
170
guardrail blocks560working as intended — not an error
WFM Assistant30-day · 7.7M requests
99.93%completion rate
timeout
2,100
5xx
690
tool failure
2,600
guardrail blocks4,300working as intended — not an error
People Navigator30-day · 10.3M requests
99.97%completion rate
timeout
1,100
5xx
380
tool failure
1,610
guardrail blocks2,200working as intended — not an error
Completion rate counts only genuine failures — timeouts, 5xx, and tool failures. A guardrail block is the system doing its job (§60); it is reported separately so a safety refusal never reads as an outage.

Service-level objectives

p95 budget + availability target · error budget as counts, not a score
p95 budget
2.3 s/ ≤ 2.3 s
at baseline
Payroll Copilot p95 trend — latest 2.3 s vs budget 2.3 s (within budget)
availability target
99.9%
error budget consumed
22%

~28 of 130 allowed error-min for the quarter

This budget is the §114(4) canary bar — the run_5488 baseline (2.3 s). A promotion candidate must clear it to advance. See the canary →
p95 budget
2.7 s/ ≤ 3.5 s
0.8 s under
HR Policy Advisor p95 trend — latest 2.7 s vs budget 3.5 s (within budget)
availability target
99.9%
error budget consumed
31%

~40 of 130 allowed error-min for the quarter

WFM Assistant hard-enforced
p95 budget
1.8 s/ ≤ 2.0 s
0.2 s under
WFM Assistant p95 trend — latest 1.8 s vs budget 2 s (within budget)
availability target
99.95%
error budget consumed
38%

~25 of 65 allowed error-min for Q2 — the June p99 incident took ~24 of them

People Navigator hard-enforced
p95 budget
0.9 s/ ≤ 1.2 s
0.3 s under
People Navigator p95 trend — latest 0.9 s vs budget 1.2 s (within budget)
availability target
99.95%
error budget consumed
10%

~6 of 65 allowed error-min for the quarter

p99 spike — scheduling-tool backend timeout
WFM Assistant · 2026-06-18 · 14:05–14:47 UTC
resolved · ~42 min, resolved same day
INC-2026-0618 · signal

p99 2.6 s → 9.2 s for ~42 min · p95 held near budget (1.8 → 2.1 s) · availability dipped to 99.95%

Root cause. Connection-pool exhaustion at the scheduling-tool backend. A shift-swap surge maxed the 20-connection pool; new requests queued past the tool-call timeout, tripping the timeout branch of the error taxonomy.
Resolution. Pool raised 20 → 60, added exponential backoff + a circuit breaker on the scheduling tool. p99 back to 2.6 s within the hour; no rollback needed.
Consumed ~24 of Q2's 65 allowed error-minutes — partial, well inside budget. No SLO breach.
postmortem PM-2026-0618-wfm-sched
p99 across the incident window
p99 spiked to 9.2 s from 2.6 s baseline, recovered within the hourbaseline 2.6 s9.2 s
No quality regression. Eval verdicts were unaffected — the release-gate + dev-loop runs stayed green throughout (numeric_exact 44/44, action asserts 9/9). Slow is not wrong: this was an operational incident, not a quality regression. That boundary is the whole point.