Concepts and technologies disclosed herein are directed to multiple feedback instance inter-coordination to determine optimal actions. According to one aspect, a system can receive a plurality of events associated with a group of feedback instances operating in a runtime. The system can examine the plurality of events to determine if a match exists between the plurality of events and an optimization plan. If so, the system can instruct a further system to realize the optimization plan. If not, the system can identify an extensibility of a feedback instance in the group of feedback instances. The extensibility can extend functionality of the feedback instance to provide additional information responsive to an event of the plurality of events. The system can update a feedback instance model associated with the feedback instance for which the extensibility was identified and can instruct the further system to extend the scope of the feedback instance.