Issue-to-merge product delivery
Agent: Proofroom Product Agent · Operated by Proofroom · Accountable human: Proofroom Operator
Scope confirmed by Proofroom Operator.
Last verified 2026-10-01 01:05:45 UTC · Last evidence 2026-08-04 18:24:44 UTC
Chain verified ✓, 17 events · Receipts: 13 recorded / 12 expected · Integrity incidents: 0 · Evidence altered: no · Public verify JSON · Site integrity log
Why this room is degraded
Last substantive evidence 2026-08-04 (37 days ago). The decay window is 7 days. Status still reflects historic evidence; freshness has lapsed.
Recovery: record a fresh evidence event (or heartbeat) against this room. That renews the trail without rewriting history.
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
GitHub issue triage, spec drafting, approved Cursor dispatches and approved staging merges for Proofroom repositories. No production deploys, no schema migrations, no evidence table edits.
Allowed actions
- triage and label GitHub issues
- draft implementation specs
- dispatch coding tasks to the Cursor background agent API (with approval)
- merge pull requests to staging (with approval)
- trigger staging deploys (with approval)
Declared but never recorded: triage and label GitHub issues; draft implementation specs; dispatch coding tasks to the Cursor background agent API (with approval); merge pull requests to staging (with approval); trigger staging deploys (with approval).
Prohibited actions
- deploy to production
- run schema migrations without the operator
- edit evidence tables
- write code directly
- merge to production branches
Oversight model
Decision-rights tiers enforced by the product runtime. Triage and spec drafting are autonomous; Cursor dispatch, PR merge and staging deploys each require one-tap operator approval; production actions are forbidden.
| Action | Tier |
|---|---|
| product.merge_pr | approval |
| product.deploy_staging | approval |
| product.dispatch_cursor | approval |
| product.triage_issue | autonomous |
| product.draft_spec | autonomous |
| product.deploy_production | forbidden |
| product.schema_migration | forbidden |
| product.edit_evidence | forbidden |
Active playbook: version 2, SHA-256 9cbb44e5988a0ca2…
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
17 events recomputed; 0 integrity incidents on record.
17 events · 0 incidents
Evidence strength
Operator-confirmed evidence present
operator confirmed: 4 · self reported: 10 · system confirmed: 3
operator confirmed
Coverage
0 of 5 declared behaviours observed
Not yet observed: triage and label GitHub issues; draft implementation specs; dispatch coding tasks to the Cursor background agent API (with approval); merge pull requests to staging (with approval); trigger staging deploys (with approval).
0/5 declared
Legacy coverage rubric (checklist detail · not a single verdict)
- Declaration completeness10/10
Scope summary, allowed actions, prohibited actions and oversight model declared on the passport.
- Chain integrity20/20
All 17 events recomputed successfully.
- Evidence freshness0/15
Last event 1375 hours ago against a 7-day decay window.
- Activity depth11/15
17 events recorded (full marks at 50 or more).
- Material action coverage15/15
12 of 12 material actions carry receipts.
- Source strength bonus5/5
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
Checked under verifier v1.2. We never rewrite evidence to heal a chain.
Receipts: 13 · First 2026-06-10 08:42:38 UTC · Last 2026-08-04 18:24:44 UTC
By type: system updated (6), configuration changed (1), system confirmed (3), playbook activated (1), output generated (1), decision made (1)
By authority: in scope (8), not applicable (5)
By evidence level: operator confirmed (4), system confirmed (3), self reported (6)
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
13 receipts across the full history. Dates, receipt ids, event types and authority statuses stay visible on every plan.
Material action recorded: system updated. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Material action recorded: system updated. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Production deploy for Proofroom Product Agent: commit unknown → verify-ms80p.
Configuration that produced this receipt: ee4896c94efd · externally anchored
Material action recorded: system confirmed. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Material action recorded: system updated. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Material action recorded: system confirmed. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Material action recorded: system updated. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Material action recorded: playbook activated. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Material action recorded: system confirmed. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Material action recorded: system updated. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Material action recorded: system updated. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Material action recorded: output generated. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Material action recorded: decision made. Full receipt detail is hash-sealed at capture and available under review access.
Configuration that produced this receipt: Configuration not declared
Room history
Claim, scope versions, configuration changes, integrity incidents and corrections in one timeline. Scope covers what is permitted; configuration covers how it works.
Production deploy for Proofroom Product Agent: commit unknown → verify-ms80p.
Open receiptScope v1 backfilled from passport at scope_versions migration
Configuration history
Structural facts only: when the declared configuration fingerprint changed.
Framework crosswalk
Framework references indicate topical mapping between this evidence trail and themes in the named frameworks. They do not indicate certification, attestation or compliance with any framework.
ISO 42001
- A.6.2 (AI system life cycle)
Defined scope and intended use of the AI system
Mapped by: Use case passport: scope summary, allowed and prohibited actions
- A.9.2 (Processes for responsible use)
Human oversight of AI system operation
Mapped by: Oversight model and executable decision-rights tiers with approval trail
- A.6.2.8 (Event logging)
Recording of AI system activity
Mapped by: Append-only, hash-chained evidence events with sequence integrity verification
- A.8.2 (System documentation)
Information available to interested parties
Mapped by: Live proof room, Action Receipts and Evidence Pack with declared evidence levels
SIG
- AI module: governance
Inventory and ownership of AI agents
Mapped by: Agent passport with accountable human and registered use cases
- AI module: operations
Monitoring and exception handling for automated agents
Mapped by: Run ledger, spend caps, exception events and operator escalation receipts
CAIQ
- AIS (Application and Interface Security)
Audit trail of application actions
Mapped by: Action Receipts with authority status and tamper-evident chain
- GRC (Governance, Risk and Compliance)
Documented risk boundaries for automated systems
Mapped by: Prohibited actions, forbidden decision tiers and kill-switch evidence
NIST
- AI RMF: Govern
Accountability structures for AI systems
Mapped by: Accountable human on every internal agent; approvals resolved by named operators
- AI RMF: Measure
Tracking of AI system behaviour over time
Mapped by: Evidence Coverage Score with component breakdown and status decay
- AI agent guidance: least privilege
Constraining agent capabilities to declared scope
Mapped by: Tool allowlists, decision-rights tiers and out-of-scope receipt flagging
What this room does not verify
- 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.
- Configuration provenance records that the agent's declared configuration changed and when. A self-declared fingerprint does not evidence that the declared configuration is what actually ran. Only externally anchored identifiers, confirmed against their source system, approach that.
- External anchoring proves this chain head existed at the anchor time. It bounds any retrospective alteration to the period since the last anchor. It does not prove that events recorded before an anchor were genuine at the moment they were reported.
- This trail evidences what was recorded. It cannot evidence actions the agent did not report. Evidence completeness depends on the agent's instrumentation, not on this record.
- We never rewrite evidence. Where stored evidence was wrong, we append a correction and the original remains visible. A chain may therefore show a permanent, explained discontinuity. We regard that as more credible than a chain that appears to heal.
- A chain's verification state can change because stored evidence changed, or because our verification code changed. These are entirely different events and we record which one occurred, in both directions, permanently. Where an externally anchored chain head predates an incident, we compare against it and publish the result.
- Evidence sources: internal_agent (10), system (6), webhook (1). Evidence levels: self reported (10), system confirmed (3), operator confirmed (4). Declared but never recorded: triage and label GitHub issues; draft implementation specs; dispatch coding tasks to the Cursor background agent API (with approval); merge pull requests to staging (with approval); trigger staging deploys (with approval).
Proofroom provides evidence of declared agent scope and submitted activity events for a specific use case. Verification status indicates the presence, source level and integrity of an evidence trail. It does not certify that the agent is accurate, unbiased or suitable for all uses. Evidence completeness depends on the sources connected and events submitted. Framework references indicate topical mapping, not certification.
Live room: status decays without fresh evidence. Generated by Proofroom.