Skip to main content
Status: planned. The incident contract is written and released in the agent’s skill bundle; the ITSM service it drives is not yet deployed.
When something is genuinely wrong, the durable record is a ticket, not a chat message that scrolls away. When a person steps in, the agent steps back. The monitoring layer decides something is wrong. The incident system turns that into a ticket with a threaded narrative. Once resolved, it also becomes a knowledge-base article the next occurrence can reuse. Notifications are the alert surface; the ticket is the truth.

​
The operating contract

Agents follow one deterministic contract so incidents stay clean and a person is never overwritten.

​
Guardrails

The agent runs the contract under the same discipline as every other write path. It uses a dry-run mode that prints what it would do instead of doing it. It also applies a rate limit of one write per finding per cycle, plus bounded reads that never pull full ticket histories into context. Credentials come from the agent’s environment and are never printed into a ticket. See the Hermes agent for the runtime that drives it.