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.

Product leaders must personally engage with AI development. Direct experience reveals unique, non-human failure modes. Unlike a human developer who learns from mistakes, an AI can cheerfully and repeatedly make the same error—a critical insight for managing AI projects and team workflow.

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.

The essential skill for AI PMs is deep intuition, which can only be built through hands-on experimentation. This means actively using every new LLM, image, and video model upon release to objectively understand its capabilities, limitations, and trajectory, rather than relying on second-hand analysis.

Unlike traditional software, AI products are evolving systems. The role of an AI PM shifts from defining fixed specifications to managing uncertainty, bias, and trust. The focus is on creating feedback loops for continuous improvement and establishing guardrails for model behavior post-launch.

Assigning error analysis to engineers or external teams is a huge pitfall. The process of reviewing traces and identifying failures is where product taste, domain expertise, and unique user understanding are embedded into the AI. It is a core product management function, not a technical task to be delegated.

Developers often test AI systems with well-formed, correctly spelled questions. However, real users submit vague, typo-ridden, and ambiguous prompts. Directly analyzing these raw logs is the most crucial first step to understanding how your product fails in the real world and where to focus quality improvements.

AI models lack novel context and frequently produce errors. The success of an AI-first product hinges on leveraging domain experts to build the model's "muscle," provide essential context, and constantly validate its output to ensure accuracy and value.

Since current AI is imperfect, building for novices is risky because they get stuck when the tool fails. The strategic sweet spot is building for experts who can use AI as a powerful but flawed assistant, correcting its mistakes and leveraging its strengths to achieve their goals.