AI Augmentation, Not Automation

In 2005, the online chess platform Playchess.com hosted a freestyle tournament with an unusual rule: any combination of humans and computers could enter. Grandmasters played alongside AI engines and hybrid teams of amateurs armed with laptops. The winners were not the grandmasters. They were not the strongest AI engines. They were two amateur players using three ordinary computers, who had developed a superior process for integrating human intuition with machine calculation. Garry Kasparov, observing the result, articulated the principle that would come to define a generation of human-AI research: "Weak human + machine + better process was superior to a strong computer alone and, remarkably, superior to a strong human + machine + inferior process." The centaur -- the mythological creature that is half human, half horse, greater than either -- had entered the business lexicon. The principle applies directly to every organisation contemplating AI: the goal is not to replace the human with the machine but to create a hybrid that outperforms both.

The Framework

The Automation Trap

Up to 60 percent of work activities could be automated, and this trend shows no signs of decelerating. Organisations pursue standardisation, streamlining, and speed. From a short-term financial perspective, automation is compelling: lower labour costs, consistent output, no sick days, no salary negotiations. One executive remarked with evident satisfaction that AI was "an absolute cost killer" for his clients.

The satisfaction is premature. Automation delivers short-term performance gains that mask four structural pathologies, each of which erodes the long-term capability of the organisation.

Pathology 1: Job fragmentation and polarisation. When AI automates the routine middle of the job spectrum -- administrative, bureaucratic, process-driven work -- the result is not a smaller, more skilled workforce. It is a bifurcated one. High-paid creative and strategic roles remain. Low-paid manual roles that are too expensive to automate remain. The middle disappears. Workers displaced from mid-level positions cannot immediately upskill to strategic roles; they fall into lower-paid work. Bargaining power erodes. Inequality increases. The socioeconomic instability that results does not stay outside the company gates -- it becomes the company's operating environment.

Pathology 2: Organisational identity crisis. AI adoption introduces a new type of worker -- the machine. Leaders must ask what kind of organisation they want to become. A company that automates everything it can, retaining humans only for tasks machines cannot yet perform, is making a philosophical statement about the value of human contribution. That statement will be heard by employees, customers, and the market. An executive at a roundtable understood this: his vision positioned AI as augmenting the reputation that customers valued in their interactions with employees -- knowledgeable, innovative, irreplaceable by a machine.

Pathology 3: Skills atrophy. The more tasks that are automated, the more boring residual human work becomes, and the greater the risk of accidents and failures. Airline pilots today fly planes that largely fly themselves. The result is not safer aviation but a pilot workforce whose manual flying skills atrophy from disuse. When the autopilot fails -- as it did for Captain Sullenberger over the Hudson River -- only deep training and experience save lives. The airline industry's response to automation has been to cut pilot training, lower salaries, and drive talent from the profession. Republic Airways in 2022 petitioned the FAA to hire less experienced pilots to address the shortage that automation-driven cost-cutting created. The request was denied. The paradox is precise: the more you automate, the more critical the remaining human skills become, and the less you invest in maintaining them.