EXHIBIT 12 / PRODUCT ANATOMY
What is OpenClaw—and what gives it authority to act?
OpenClaw is an open-source agent product that can operate through a user’s machine, messages, and accounts. A replaceable model produces proposals; the surrounding product connects channels, tools, state, permissions, and execution.
ROOM 01 / DEFINE
A product name hides four distinct kinds of authority.
- 01 / CHANNEL Who may ask?
Messaging channels and pairing or allowlists determine which senders can reach a configured agent surface.
- 02 / MODEL What may be proposed?
A selected model interprets context and proposes text or tool calls. The model is replaceable and is not the OpenClaw product itself.
- 03 / TOOL What can execute?
The active profile, allow/deny policy, sandbox, provider restrictions, and channel permissions shape which tools are visible and usable.
- 04 / EFFECT What changes persist?
Commands, browser actions, messages, scheduled jobs, and account operations can create real effects, so identity, scope, approval, and audit matter.
ROOM 02 / INSPECT
Trace a request without treating the product as magic.
This teaching trace follows documented roles. It does not connect to OpenClaw, inspect an installation, or run a command.
INGRESS
A channel identifies the requester
The gateway receives a message through a configured channel and applies the channel’s pairing, allowlist, and session rules.
Unknown senders can be stopped before their content reaches the model.
Keyboard: focus this instrument and use ← or →. It never advances by itself.
ROOM 03 / TEST
Build a bounded permission envelope.
Change four deployment facts for a hypothetical file-writing request. The browser applies a teaching policy; it never contacts OpenClaw or a filesystem.
SCENARIOIncoming request includes untrusted email text and proposes writing a summary file.
Real deployments require current documentation, threat modelling, secret handling, network controls, updates, monitoring, and incident response beyond these four controls.
ROOM 04 / VERIFY
Read product claims and permission claims at different scopes.
An extensible open-source agent
OpenClaw describes itself as acting through a user’s machine, messages, and accounts, with replaceable harness and protocol integrations.
One gateway, one trust boundary
Current documentation distinguishes tool policy, sandboxing, permission profiles, requester scope, and node execution controls.
Safety or autonomy breakthrough
The museum does not audit the codebase, certify a deployment, equate product popularity with AGI, or execute the product.
REVIEWED SOURCES