4 of 30 records. Results are T2 and above.
Take a published Copilot Studio agent back out of service, least drastic action first, when it is answering badly in front of users.
Measure the thing you are replacing before you lose access to it, gate the switch on the same questions, and set the decommission date at cutover.
The pipeline refuses a run before it starts, so the deploy has to happen from a workstation — told apart from a real failure first, and with what the manual path costs put back afterwards.
Run an integration whose credential is one account session without losing that session — a second worker on the same key reads as a hijack, and the key does not come back.