Frame your interaction with AI as if you're onboarding a new employee. Providing deep context, clear expectations, and even a mental "salary" forces you to take the task seriously, leading to vastly superior outputs compared to casual prompting.

AI excels at clerical tasks like transcription and basic analysis. However, it lacks the business context to identify strategically important, "spiky" insights. Treat it like a new intern: give it defined tasks, but don't ask it to define your roadmap. It has no practical life experience.

Generative AI, like a junior employee, is eager to please and will rush to a final deliverable without sufficient context. Leaders must manage this by iteratively providing information and explicitly stopping the AI from generating the final output prematurely, preventing low-quality "slop".

Unlike human collaborators, an AI lacks feelings or an ego. This means you should be direct, critical, and push back hard when its output isn't right. Frame the interaction as a demanding dialogue, not a polite request. You can also explicitly ask the AI to critique your own ideas from first principles to ensure a rigorous, two-way exchange.

Conceptualize Large Language Models as capable interns. They excel at tasks that can be explained in 10-20 seconds but lack the context and planning ability for complex projects. The key constraint is whether you can clearly articulate the request to yourself and then to the machine.

Vercel designer Pranati Perry advises viewing AI models as interns. This mindset shifts the focus from blindly accepting output to actively guiding the AI and reviewing its work. This collaborative approach helps designers build deeper technical understanding rather than just shipping code they don't comprehend.

Treat your AI like a brilliant intern who has raw talent but lacks experience and memory. This mental model encourages providing clear instructions and assuming best intentions while being prepared to constantly remind it of past decisions and project constraints, preventing it from making repeated, simple mistakes.

General-purpose AI assistants produce inconsistent output. Instead, define AI agents with specific roles, boundaries, and quality gates, much like onboarding a new engineer with a clear job description. This disciplined approach leverages how LLMs are trained, leading to more reliable and predictable results within the SDLC.

Don't blindly trust AI. The correct mental model is to view it as a super-smart intern fresh out of school. It has vast knowledge but no real-world experience, so its work requires constant verification, code reviews, and a human-in-the-loop process to catch errors.