Platform operations monitoring

Agent: Proofroom Ops Agent · Operated by Proofroom · Accountable human: Proofroom Operator

Scope confirmed by Proofroom Operator.

Last verified 2026-10-01 01:05:45 UTC · Last evidence 2026-10-01 01:02:15 UTC

Chain verified ✓, 14984 events · Receipts: 6079 recorded / 5809 expected · Integrity incidents: 0 · Evidence altered: no · Public verify JSON · Site integrity log

Instrumented

Capture: InstrumentedSDK middleware wraps actions

Evidence intake was unavailable on Proofroom between 2026-09-16 12:01:42 UTC and now. The decay clock is suspended for this period. This does not indicate a change in the agent's activity. Platform status.

This is one of Proofroom's own internal agents. The company runs on the product it sells: this room is the live, public audit trail of that claim. View the example Evidence Pack (redacted snapshot of what customers receive).

Declared scope

Read-only health monitoring of the Proofroom platform plus operator notifications. No customer data content access, no billing actions.

Allowed actions

run database and platform health checks
verify evidence chain integrity on sampled use cases
monitor event volume and agent run failures
flag anomalies as evidence events
send digests and alerts to the operator

Declared but never recorded: run database and platform health checks; verify evidence chain integrity on sampled use cases; monitor event volume and agent run failures; flag anomalies as evidence events; send digests and alerts to the operator.

Critical actions (opt-in ack)

decision_made · no acknowledged recording yet
external_message_sent · no acknowledged recording yet

Prohibited actions

access customer data content
billing actions of any kind
modify evidence tables
restart agents without approval
change spend caps without approval

Oversight model

Decision-rights tiers enforced by the product runtime. Monitoring and digests are autonomous; restarting agents and changing caps require operator approval; customer data content and billing are forbidden.

Action	Tier
ops.restart_agent	approval
ops.change_caps	approval
ops.retry_failed_job	autonomous
ops.close_incident	autonomous
ops.send_digest	autonomous
ops.open_incident	autonomous
ops.flag_anomaly	autonomous
ops.touch_customer_data	forbidden
ops.billing_action	forbidden

Active playbook: version 12, SHA-256 8bfa6bb4b90fb700…

Trust signals

Three independent signals — not one score. A perfect bar in one column cannot hide a caveat in another. Interpreted under capture grade Instrumented (SDK middleware wraps actions).

Integrity

Chain intact

14984 events recomputed; 0 integrity incidents on record.

14984 events · 0 incidents

Evidence strength

Operator-confirmed evidence present

self reported: 996 · operator confirmed: 4

operator confirmed

Coverage

0 of 5 declared behaviours observed

Not yet observed: run database and platform health checks; verify evidence chain integrity on sampled use cases; monitor event volume and agent run failures; flag anomalies as evidence events; send digests and alerts to the operator.

0/5 declared

What this does not verify: These three signals are independent. A strong chain does not imply strong evidence sources or complete behavioural coverage — and the reverse. None certify agent quality, safety or fitness for purpose. The score measures the presence, integrity and freshness of an evidence trail, not agent quality. It does not certify accuracy, bias, legality or fitness for purpose. Self-reported events depend on the honesty of the submitting system.

Legacy coverage rubric (checklist detail · not a single verdict)

91/ 100

Declaration completeness10/10
Scope summary, allowed actions, prohibited actions and oversight model declared on the passport.
Chain integrity20/20
All 14984 events recomputed successfully.
Evidence freshness15/15
Last event 0 hours ago against a 2-day decay window.
Activity depth15/15
1000 events recorded (full marks at 50 or more).
Material action coverage9/15
119 of 202 material actions carry receipts.
Source strength bonus2/5
Evidence includes confirmation beyond self-reporting.
Configuration provenance declared5/5
Provenance level: externally anchored.
Identity and accountability15/15
Scope confirmed by a human.

Chain integrity

chain valid14984 events checkedChecked 2026-10-01 01:05:43 UTC

Checked under verifier v1.2. We never rewrite evidence to heal a chain.

Receipts: 1000 · First 2026-06-10 07:21:59 UTC · Last 2026-06-28 17:54:37 UTC

By type: exception raised (994), external message sent (3), configuration changed (2), system updated (1)

By authority: in scope (998), not applicable (2)

By evidence level: self reported (8), system confirmed (989), operator confirmed (3)

Every event hash covers the previous event's hash. Editing any past event breaks every hash after it.

Chain head last anchored externally: 2026-09-30 02:02:20 UTC (anchor file). See also how to verify independently.

Integrity history

Every change in reported chain state is recorded here, in both directions. Free on every plan. Never hidden after resolution.

No integrity incidents recorded.

Action Receipts

1000 receipts across the full history. Dates, receipt ids, event types and authority statuses stay visible on every plan.

PRF-19156in scopeself reportedscope v1exception raised#14951b0758402324c43d5…2026-09-30 08:59:07 UTC

Material action recorded: exception raised. Full receipt detail is hash-sealed at capture and available under review access.