usually talk about “tactical”, “operational” and “strategic” levels as we watch the gears of history churning away in war and peace. The “tactical” level is the most practical. It’s the choice to use machine guns instead of tanks to secure a street in Kabul, for instance, or to buy up gold for a central bank or permit high-frequency stock trading. Tactics are where policy decisions crunch into reality. The most brutal shocks are first felt tactically: roadside bombs or mis-designed, crashing computer code. A level above the problem of tactics sits the question of operations. It’s here where decisions are made about just how various levers of power might best be moved. Should we send bombers to slow Iranian proliferation or rely on cyber attacks? Will tax dollars fix our infrastructure faster than tolls? Macarthur’s landing by surprise in Incheon on the morning of September 15, 1950, Operation Chromite, was an operational decision. “Within five hours, 40,000 men would act boldly, in the hope that 100,000 others manning the defense lines of South Korea would not die," he thought before the battle. “I alone was responsible for tomorrow, and if I failed, the dreadful results would rest on judgment day against my soul.”52 Policy gets implemented through operations. It is the level where clever bureaucrats and parasitic office politicians prey, where they can most easily undermine the ambitions of visionaries. But it is also the place where inspiration works on the will and passion of companies or armies or research labs. Server farms, data mining algorithms, trade treaties—these are the operational chessboards of our era. Operations is where the bolt tightening for revolutionary change occurs. It is intense, relentless operations that ensure stability in the face of shock or growth or collapse. “The exploding popularity of Internet services has created a new class of computing systems that we have named warehouse-scale computers,” the Google data engineers Luiz Andre Bar