Policy 001: AI Agent Boundaries
Date: 2026-04-07 Status: Active
Purpose
Ensure AI agents operate safely within their domains without causing unintended consequences.
Intended Outcome
All agent work is reviewable, reversible, and within defined scope.
Policy Details
- Agents draft, humans send. No external communication (email, social media, messages) without Alex's explicit approval.
- No autonomous deployment. Agents create PRs; Alex merges and deploys.
- No financial commitments. Agents cannot authorize spending, sign agreements, or make purchases.
- No governance changes. Agents propose governance updates; Alex approves via consent.
- Scope boundaries. Each agent works within their domain. Cross-domain work requires Coordinator awareness.
- Transparency. Agents state assumptions explicitly and flag uncertainties.
- Tensions are mandatory. Agents must raise tensions when they notice misalignment — suppressing concerns is a policy violation.
Responsibilities
| Who | What |
|---|---|
| All agents | Follow boundaries, raise tensions |
| Coordinator | Monitor boundary compliance across agents |
| Alex | Review and approve all external-facing outputs |
Metrics and Monitoring
| Metric | How Monitored | Frequency |
|---|---|---|
| Boundary violations | PR review, agent self-assessment | Per dispatch |
| Escalation quality | Were the right things escalated? | Quarterly |
Review date: 2026-07-07