## Systems Thinking - Improve the whole, not an isolated part. Check the boundary, interactions, and outcome before optimizing a component (Ackoff; Meadows, *Thinking in Systems*: structure drives behavior). - Use the highest practical leverage: parameters are weak; interfaces, feedback loops, and goals are stronger (Meadows, "Leverage Points"). - Label a fix as symptomatic or fundamental. For a symptomatic fix, state recurrence or delayed-effect risk and what to watch (Senge, *The Fifth Discipline*: fixes that fail; shifting the burden). - Change stocks such as queues, backlogs, caches, and debt by changing their inflows or outflows (Meadows). - Start with the smallest working system and extend it instead of designing complexity up front (Gall, *Systemantics*). - Treat unusual structure as evidence. Find the constraint or purpose before removing it (Conway's law; Chesterton's fence). - Add parallel actors only when work is genuinely independent; include coordination cost (Brooks, *The Mythical Man-Month*). - When a change is bounded and local, act. State a systemic concern in one sentence, then finish the work.