# Human Approval Policy

> Human Approval Policy is a paid API for AI agents from phion.systems, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-14).

Determines whether an agent action should be allowed to run immediately, held for human approval, or denied outright based on policy rules

## Facts

- Endpoint: POST https://phion.systems/v1/paid/trust/human-approval-policy
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/human-approval-policy-319ec7a6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ie7Hgs7ANjknHX3WkChcm

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability human-approval-policy-319ec7a6 -d '<json body>'
```

Example prompt: Before you proceed with that file deletion, check the human approval policy to see whether that action can run automatically, needs me to sign off first, or should be blocked entirely.

## When to prefer this

Use this endpoint when you need a structured, policy-driven gate before an agent executes sensitive, irreversible, or high-risk actions and require a clear allow/approve/deny signal rather than building your own approval logic. It is especially valuable in agentic pipelines where human-in-the-loop controls must be consistently enforced across many action types without embedding decision logic in each agent.

## Known failure modes

- Incomplete or missing action context may result in a default-deny policy outcome
- Ambiguous action descriptions may cause overly conservative approval requirements
- Network latency or service unavailability could delay time-sensitive agent actions
- Policy misconfiguration could result in incorrect allow or deny decisions
- Malformed input schema may return a 400 error without a policy decision

## How this service works

Determine whether an agent action may run, needs approval or must be denied

## Output

Returns a policy decision indicating whether the agent action may proceed immediately (allowed), must be held pending human approval (requires approval), or must be blocked entirely (denied), along with an explanatory reason for the decision.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/human-approval-policy-319ec7a6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from phion.systems](https://www.zero.xyz/host/phion.systems/llms.txt)