Security
5 engineering articles on security from building and running Swarm 357 in production.
Scenarios20 July 2026
Scenario: a support layer where Bash stays denied
Triage, macro drafting, and escalation summaries with no shell access at all. What the support layer can do without it, and the one case where a human unlocks a command.
API6 July 2026
A FastAPI agent API with SSE, fail-closed auth, and redacted reads
Streaming agent events over server-sent events, authenticating writes without breaking the stream, and returning useful public telemetry without leaking task content.
Deployment12 May 2026
Deploying a Claude agent runtime on Railway
Split the API from the landing site, keep write keys server-only, force simulate on the public demo, and let the container set server mode so Bash fails closed. A production deploy walkthrough.
Security24 March 2026
Human-in-the-loop approvals for autonomous agents
A durable ApprovalRecord, a control plane on both CLI and HTTP, and timeouts that reject. How to put a person in front of side effects without stalling every run.
Security10 March 2026
Why your agent needs a bash policy gate
Thirteen patterns, argv-level validation, and a deny-by-default posture in production. What a bash policy gate stops, and the three things it will never stop.