← The Factory

Execution Environments, Identity & Secrets

Isolated, ephemeral execution with scoped credentials and no production secrets in the model reach.

high confidence

Confidence: high. Evidence: production telemetry and case study. Last substantive change: 2026-07.

This subsystem owns where and how agent work runs: the sandbox, the credentials, and the boundaries that cap what an agent can do regardless of what it decides to do.

The conclusion

Default to isolated, reproducible, short-lived execution with filesystem and network boundaries, scoped credentials, and no production secrets directly available to the model. Containment is the last line of defense when verification and judgment fail, and it must be architectural rather than dependent on approval prompts.

How the thinking got here

Local developer permissions gave way to per-action prompts, then to sandboxes, containers, and sealed virtual machines, then to credential brokers and containment matched to blast radius. The lesson that forced this progression is blunt: an irreversible action can complete faster than any human can intervene, so the boundary has to exist before the action, not after.

Credible alternatives, and when each is right

Approach Right when
Host execution with approvals trusted, owned, low-risk work
OS sandbox light isolation is enough
Container reproducibility and parallel safety
Sealed virtual machine high-risk or untrusted code
Remote ephemeral environment scale and clean-slate runs
Air-gapped or simulated environment maximum blast-radius control

Where it fails and what we still don't know

Failures include an irreversible destructive action reachable without containment, covert channels, and secrets exposed to a context that can be injected. First-party security engineering strongly favors containment over approval fatigue; environment fidelity remains a practical trade-off. Open questions include sandbox-escape testing, dependency and network policy, identity attribution, and secretless workflows.

What would change our mind

Evidence that human approval at production volume reliably prevents irreversible mistakes would soften the case for architectural containment. The current evidence points the other way.

Evidence and further reading