double-loop-execution-reviewer

Generate an after-action review by reconstructing the completed task episode using a double-loop learning framework, which evaluates execution findings and framing recommendations to produce an evidence-based retrospective.

Double-loop learning assesses whether goals, assumptions, and working rules should change for the next iteration, moving beyond simple execution adjustments to fundamentally reframe how future tasks are approached and executed.

Create a handoff-ready output by evaluating the completed task's execution history and evidence, structuring the findings into a concise summary that explicitly defines ownership and a concrete next action for the receiving team.

Yes, the retrospective framework applies to tasks with execution history across operations, debugging, planning, and writing, evaluating the produced artifacts to generate an improvement memo with a clear continuation path.

The best way to evaluate completed work is applying a double-loop learning framework to compare intended outcomes against actual results, yielding structured execution findings and framing recommendations with explicit ownership.

You need a double-loop retrospective when a completed task requires evaluating not just execution gaps, but also whether the underlying goals, assumptions, and working rules should change before starting the next iteration.