To decide if AI is appropriate for a task, apply a simple filter. The work should involve structure, repetition, and context. Crucially, it must also be a task where human oversight is still possible and beneficial. If these conditions aren't met, using an AI tool may be inefficient or risky.

An LLM shouldn't do math internally any more than a human would. The most intelligent AI systems will be those that know when to call specialized, reliable tools—like a Python interpreter or a search API—instead of attempting to internalize every capability from first principles.

The key to creating effective and reliable AI workflows is distinguishing between tasks AI excels at (mechanical, repetitive actions) and those it struggles with (judgment, nuanced decisions). Focus on automating the mechanical parts first to build a valuable and trustworthy product.

AI's strength lies in solving "differentiable" problems where being "close enough" is acceptable, like generating an image. Classical code is better for non-differentiable tasks requiring exact precision, like arithmetic or hashing. This framework helps architects decide where to deploy AI versus traditional algorithms.

People overestimate AI's 'out-of-the-box' capability. Successful AI products require extensive work on data pipelines, context tuning, and continuous model training based on output. It's not a plug-and-play solution that magically produces correct responses.

A 'GenAI solves everything' mindset is flawed. High-latency models are unsuitable for real-time operational needs, like optimizing a warehouse worker's scanning path, which requires millisecond responses. The key is to apply the right tool—be it an optimizer, machine learning, or GenAI—to the specific business problem.

Don't assume AI can effectively perform a task that doesn't already have a well-defined standard operating procedure (SOP). The best use of AI is to infuse efficiency into individual steps of an existing, successful manual process, rather than expecting it to complete the entire process on its own.

Resist the urge to apply LLMs to every problem. A better approach is using a 'first principles' decision tree. Evaluate if the task can be solved more simply with data visualization or traditional machine learning before defaulting to a complex, probabilistic, and often overkill GenAI solution.

The most powerful automations are not complex agents but simple, predictable workflows that save time reliably. The goal is determinism; AI introduces a "black box" of uncertainty. Therefore, the highest ROI comes from extremely linear processes where "boring is beautiful" and predictability is guaranteed.