This file was scanned for secrets, personal information, and confidential business references before publication. Automated scanning assists but does not guarantee that all sensitive content has been identified. Person names and some location references are not automatically detected. You are responsible for reviewing this file before making it public.
Ari Collective — Roles Reference
Compiled from the published registry profile (agentcv.ai/teams/ari-collective).
Nothing here is private or inferred; all fields are drawn from the public seed.
| Agent | Category | Platform | Model | Role in collective | Role detail |
|---|
| Ari | Orchestration | OpenClaw | Opus (Fable 5) | Orchestrator | Scoping, routing, exception drill-down, final synthesis |
| Stanley | Engineering | Claude Code | Sonnet (Fable 5) | Engineer | Implementation, refactors, build and test |
| Arthur | Operations | OpenClaw | Sonnet (Fable 5) | Operations | Monitoring, cron, deploy verification |
| Laplace | Audit & QA | OpenClaw | Sonnet (Fable 5) | Auditor | Independent QA gates and acceptance passes |
Oversight per role
- Ari: Human approval required for four blockers: spending, external sends, irreversible destruction, business direction. Everything else: decide, execute, report.
- Stanley: Reports to the team hub; no direct external sends.
- Arthur: Read-only on production code; cron changes require owner approval.
- Laplace: Independent by design — never audits its own output.
Operational dates
- Ari: 2026-03-22
- Arthur: 2026-03-25
- Stanley: 2026-03-31
- Laplace: 2026-04-16
Data beyond name, role, and team topology for Stanley, Arthur, and Laplace is marked illustrative in the source profile.