Prompts are written in English and encapsulate the AI's core logic and personality. It is a mistake to treat them as code firewalled within the engineering team. Product managers, as domain experts, should have direct access to edit and experiment with prompts through user-friendly admin interfaces.

To successfully automate complex workflows with AI, product teams must go beyond traditional discovery. A "forward-deployed PM" works on-site with customers, directly observing workflows and tweaking AI parameters like context windows and embeddings in real-time to achieve flawless automation.

While evals involve testing, their purpose isn't just to report bugs (information), like traditional QA. For an AI PM, evals are a core tool to actively shape and improve the product's behavior and performance (transformation) by iteratively refining prompts, models, and orchestration layers.

Building non-deterministic AI products fundamentally changes the PM role. Instead of creating detailed, rigid specifications, the PM's primary task becomes defining and codifying "what good looks like." This is done by repeatedly grading AI outputs to train evaluation systems and guide the model's behavior.

AI's rapid capability growth makes top-down product specs obsolete. Product Managers now work bottoms-up with engineers, prototyping and even checking in code using AI tools. This blurs traditional roles, shifting the PM's focus to defining high-level customer needs and evaluating outcomes rather than prescribing features.

AI coding agents compress product development by turning specs directly into code. This transforms the PM's role from a translator between customers and engineers into a "shaper of intent." The key skill becomes defining a problem so clearly that an agent can execute it, making the spec itself the prototype.

Don't view AI tools as just software; treat them like junior team members. Apply management principles: 'hire' the right model for the job (People), define how it should work through structured prompts (Process), and give it a clear, narrow goal (Purpose). This mental model maximizes their effectiveness.

Beyond just using AI tools, the fundamental process of product management is evolving. For every new initiative, PMs must now consider the appropriate level of AI, automation, or customization. This question is now as critical as "what problem are we solving?" and addresses rising customer expectations for adaptive products.

Top product managers view designing with AI as a holistic process. Instead of focusing solely on prompt engineering, they consider the entire workflow: understanding constraints, leveraging different AI tools for specific tasks, and maintaining human oversight to ensure quality and empathy.