Presented with the "LinkedIn for AI" problem, the designer's first step isn't visual design. It's product strategy: clarifying the core objective (e.g., matchmaking, certification), identifying the target user groups (job seekers, employers), and defining what "a good match" even means in this new context.
AI prototyping doesn't replace the PRD; it transforms its purpose. Instead of being a static document, the PRD's rich context and user stories become the ideal 'master prompt' to feed into an AI tool, ensuring the initial design is grounded in strategic requirements.
Robbie Stein's product-building framework focuses on three pillars: 1) Go deep on user motivation (Jobs To Be Done). 2) Use data to dissect problems with rigor. 3) Prioritize clear, intuitive design over novel but confusing interfaces. Humility is the foundation for all three.
Don't design solely for the user. The best product opportunities lie at the nexus of what users truly need (not what they say they want), the company's established product principles, and its core business objectives.
When building complex AI systems that mediate human interactions, like an AI proctor, start by creating a service map for the ideal human-to-human experience. Define what a great real-world proctor would do and say, then use that blueprint to design the AI's behavior, ensuring it's grounded in human needs.
AI and cataloging tools have compressed the competitive research phase from days to minutes. This frees designers from tactical UI comparison and empowers them to focus on higher-level strategic work: crafting product narrative and system architecture, a role previously reserved for senior leadership.
Perplexity's VP of Design, Henry Modiset, states that when hiring, he values product intuition above all else. AI can generate options, but the essential, irreplaceable skill for designers is the ability to choose what to build, how it fits the market, and why users will care.
With AI, designers are no longer just guessing user intent to build static interfaces. Their new primary role is to facilitate the interaction between a user and the AI model, helping users communicate their intent, understand the model's response, and build a trusted relationship with the system.
Technical implementation is becoming easier with AI. The critical, and now more valuable, skill is the ability to deeply understand customer needs, communicate effectively, and guide a product to market fit. The focus is shifting from "how to build it" to "what to build and why."
Instead of writing a traditional spec, the product team at Yelp starts by writing an ideal sample conversation between a user and the AI assistant. This "golden conversation" serves as the primary artifact to work backward from, defining the desired user experience before any technical requirements.
Instead of immediately building, engage AI in a Socratic dialogue. Set rules like "ask one question at a time" and "probe assumptions." This structured conversation clarifies the problem and user scenarios, essentially replacing initial team brainstorming sessions and creating a better final prompt for prototyping tools.