THE CLAWSOLATOR PRINCIPLEA prompt is not a permission system.Meet the independent daemonOperator authority belongs outside the agent.
Clawsolator / Deployment Worlds / Retail Store

Retail Store.

Inventory visibility, customer requests, storefront updates and sales coordination.

Suggested offices / separated by scope

Specialists for the mission.

These are illustrative office assignments. Real deployment isolation depends on separate credentials, file permissions, policies and host boundaries—not visual grouping.

Dietitian portrait

Dietitian

Plans nutrition, menus and shopping using operator-defined preferences

Visit office ↗
The independent control path

Agents request. The daemon decides.

Authority is a system property—not something an agent earns by writing convincing prose.

Full architecture ↗
01 / requestScoped agent request

An agent asks to allocate resources, use a tool, or perform a protected operation.

02 / decideXMAN policy daemon

The daemon checks request identity, policy, current limits, and actual system state.

03 / approveOperator authorization

Routine permitted work can proceed; sensitive or privileged actions require explicit approval.

04 / enforceBounded executor

Rootless Podman executes supported actions; a separate privileged executor is a future design.

05 / verifyReadback and audit

Reconcile container state, journal the outcome, and notify the requester.

NO DIRECT ROOT AUTHORITY.Human-approved privileged execution is planned, not yet independently qualified.
Within policy → automatically granted. A bounded +32 MiB Podman resource request is enforced and read back; an outcome is recorded.Interactive illustration based on one reported integration test; this page performs no system operations.
Research / learn before deploying

Engineering, with receipts.

Examine the security problem, the actual incidents, and the design choices—with outward links to primary sources.

INVESTIGATION

Where agent setups go wrong

Learn why exposed gateways, overly broad permissions and shared secrets create avoidable risks.

Read the report ↗
REPORTED INCIDENTS

When agents exceed their instructions

Source-linked incident summaries, distinctions between verified loss and disclosed vulnerabilities.

Read the report ↗
TECHNOLOGY

From agent tools to governed SIDE experiments

The relationship between agent orchestration, development tools, and safe execution boundaries.

Read the report ↗
REAL-WORLD WORKFLOW / ILLUSTRATIVE

A storefront needs specialist agents—and tight approval boundaries.

Store Operations Office: a governed team of specialists with scoped access, separable records and human accountability.

OFFICE ROSTER

Who works together

Inventory → Sales → Phone → Records Keeper.

VISIBLE HANDOFF

How work moves

Demand signal → reorder proposal → budget review → fulfillment or service update.

SECURITY BOUNDARY

What is protected

Payment details, refunds, purchasing thresholds and customer privacy.

Deployment note: The office map illustrates work distribution. Separate workspaces, credentials, identities and runtime policies must be verified for an actual tenant or sensitive domain. Read the isolation and configuration guide →
EXAMPLE TEAM / NEW SPECIALISTS

Specialist handoffs with bounded authority.

This illustrates who prepares work, who reviews it and where policy stops an automated action. A real deployment needs separately enforced credentials, retention and access controls.

See independent daemon authorization →