Many tasks branded as 'AI automated' secretly rely on human intervention. To reveal this dependency and identify the real accountability structure, simply ask who is responsible for errors produced by the system. This forces the organization to name the person still in the loop.

A key risk of AI is the atrophy of human skills like judgment and taste. Instead of optimizing solely for efficiency, product teams should design AI-powered workflows with intentional friction that encourages users to practice and develop their core competencies, preventing them from becoming mere QA checkers for an algorithm.

A key challenge in AI adoption is not technological limitation but human over-reliance. 'Automation bias' occurs when people accept AI outputs without critical evaluation. This failure to scrutinize AI suggestions can lead to significant errors that a human check would have caught, making user training and verification processes essential.

To avoid over-reliance on AI, adopt a two-tiered approach. For critical analysis or high-accountability decisions, formulate your own thoughts first. Then, use AI to challenge your assumptions and find what you missed. For the 80% of low-stakes, routine work, delegate it to AI to eliminate noise and increase focus.

The old model of a human simply approving an AI's output is obsolete. A "human at the helm" approach is needed, where leaders strategically decide where and when to insert human judgment into complex, multi-step AI workflows, acting as a director rather than a final gatekeeper.

For complex, high-stakes tasks like booking executive guests, avoid full automation initially. Instead, implement a 'human in the loop' workflow where the AI handles research and suggestions, but requires human confirmation before executing key actions, building trust over time.

The concept of "human-in-the-loop" is often misapplied. To effectively manage autonomous AI agents, companies must map the agent's entire workflow and insert mandatory human approval at critical decision points, not just as a final check or initial hand-off.

Instead of supervising every step, the human's most leveraged role is to act as a gatekeeper at critical junctures. The AI system handles all intermediate work, presenting a complete package for a single, high-stakes decision. This maximizes human judgment and minimizes micromanagement.

Contrary to the goal of full automation, the most effective AI workflows intentionally preserve points of friction. These moments—where a human must intervene, check intent, or re-steer the process—are crucial for maintaining control and ensuring the output aligns with strategic goals, preventing the system from running unchecked in the wrong direction.