copilot-credit-spike-contain
The procedure as a graph, on its own page — zoom it, print it, send somebody the address. Back to the record for the steps, the trust panel and the provenance.
Procedure
The same procedure, read in order
- start start. Goes next to s1
- check Confirm the spike in the consumption grid. Goes on_fail to __end_aborted; next to s2
- end aborted. Terminal
- check Check for an existing per-agent limit. Goes on_fail to s9; next to s3
- action Apply or lower the per-agent limit, RW (reversible-write). Goes on_fail to s9; next to s4
- decision Is consumption still rising?. Goes if rising to s5; if default to s6
- action Disable the agent in its environment, DEL (destructive), requires approval. Goes rollback to s7; on_fail to s9; next to s6
- action Re-enable the agent, RW (reversible-write). Goes next to __end_success
- check Determine the cause before re-enabling. Goes on_fail to s9; next to s8
- escalate Escalate to the Power Platform admin. Terminal
- action Record the incident and its resolution, RW (reversible-write). Goes next to __end_success
- end success. Terminal