Five things my 13 AI agents are never allowed to do

Description and use

The author implemented a five‑gate system to control 13 AI agents, ensuring safe autonomy and full auditability via one‑page contracts and an immutable ledger.

Problem

Managing autonomous AI agents risks uncontrolled actions that can incur costs, expose secrets, or cause irreversible damage.

Outcome

The gate framework prevented unauthorized actions, maintained auditability, and allowed agents to operate autonomously within safe boundaries, producing 1,235 items while keeping the human operator in control of critical decisions.

Workflow

• Define five gates: money, auth, external sends, scheduled automation, destructive changes.
• Create one-page contract per agent specifying owner, mandate, data access, gates, escalation, kill rule.
• Maintain a single append-only ledger recording every item with status.
• When a gated action is needed, draft an envelope detailing the case, hard cap, stop-loss, and log tagging.
• Human reviews envelope, approves or rejects, and executes the action if approved.
• Monitor ledger for escalations and failures.
• Iteratively widen gates by adding envelopes as trust grows.

Evidence

People usually ask how I keep that from going wrong. The honest answer is boring: a short list of things no agent does on its own, and a long list of things they do without asking.

Source

The five gates: Money going live, Auth and secrets, External sends and posting, Scheduled automation, Destructive or irreversible change.

Source

Every agent has a one-page contract before it runs: owner, mandate, cadence, the data it may read and may never see, where it writes, which gates apply, who it escalates to, and a kill rule.

Source

One append-only ledger is the audit trail. One line per item: date | item ID | source | project | STATUS | note, where STATUS is BUILT, PARTIAL, ESCALATED or KILLED.

Source