THE CLAWSOLATOR PRINCIPLEA prompt is not a permission system.Meet the independent daemonOperator authority belongs outside the agent.
Clawsolator home / Operator guide / human-in-the-loop
Operator guide / human-in-the-loop

Human-in-the-loop approvals that agents cannot simply talk around.

A confirmation message inside a chat is not the same as an enforced approval. A meaningful approval workflow captures the exact proposed action, sends it to a separate trusted review path, applies a scoped decision and records what happened.

Direct answer

An AI agent approval workflow is an authorization protocol: a bounded agent proposes an operation; a trusted policy/manager checks the request; a human approves or rejects sensitive changes; only the permitted action executes, and the outcome is logged. It should not be possible to turn the approval off by changing a prompt.

What should require review?

HOST / PRIVILEGE

Root and package operations

Privilege changes, host scripts, service replacement, package installs and persistent system configuration.

DATA / DESTRUCTIVE

Deletion and irreversible changes

Removing messages, modifying protected records, mass edits, database mutations and broad filesystem writes.

EXTERNAL / REPUTATION

Publishing and outbound actions

Posting to production websites, sending external emails, disclosing confidential information and spending funds.

ACCESS / EXPANSION

Changing an agent's powers

New credentials, scopes, network access, skill installations, shared workspace mounts and privileged devices.

From request to recorded result

1

Submit a typed request

The agent names the intended operation and target; arguments are validated and associated with its identity. Arbitrary prose alone does not authorize execution.

2

Apply automatic boundaries

The manager checks whether the operation is permitted under the saved policy, allocated resources and allowed targets. Deny unsupported or unclear requests rather than interpreting them optimistically.

3

Present a review packet

The operator sees purpose, exact proposed commands, likely side effects, requested privilege, and alternative responses. Absence of a response is not consent.

4

Execute only what was approved

Bind approval to the proposed operation and verify results. A changed script, target or authority level should need new review.

5

Preserve evidence and recovery state

Store decisions and execution logs durably, reconcile interrupted work, and report partial failure instead of claiming success prematurely.

What XMAN implements—and what must be tested

XMAN 0.4.76a1 source describes special requests in a durable operator inbox and a daemon-mediated manager path, along with resource-policy choices. This is a development alpha; each deployment must verify actual socket permissions, process ownership, sandbox boundaries, host-script authorization and service-restart behavior.

Are approvals sufficient to stop prompt injection?

No. They can prevent untrusted instructions from directly causing certain high-risk actions if the boundary is correctly enforced. Prompt injection can still influence an agent's analysis or proposed request, and an operator can still approve a harmful change. This is why skill review, least privilege, authentication, network policy, context separation and human judgment also matter.

Independent technical answers / source-informed

Know what the agent can do. Know who decides.

Four concise paths through the architecture—written for operators, developers, security teams and evaluators. Each distinguishes configured controls from goals that still need testing.

NEW RESEARCH / DOCUMENTED OPERATOR FRUSTRATIONS

What users asked the systems to do

Firsthand issue reports, exact failure symptoms, the proposed engineering response and explicit verification limits.

Approval popup complaints →