In an agentic world, the core AI model becomes a commodity. The defensible product is the curated experience layer built on top of it—the guardrails, instructions, and personality that define the user interaction and differentiate the offering.

The high-fidelity AI prototype is becoming the primary document for communicating user experience. The Product Requirements Document (PRD) is evolving to focus on edge cases and provide structured context that can be fed back into the AI for future iterations.

Companies must now design their products, from documentation to onboarding, for a new primary user: the AI agent. This "Agent Experience" (AX) is critical because agents are how a new, massive user base will interact with and build upon platforms, making it a product's North Star.

For tools designed for AI interaction, the ease with which an agent can use the product (AX) is as critical as the user experience (UX) for humans. This can be improved by directly asking the agent for feedback on how to make the product more ergonomic for it.

The quality of AI-generated products depends on the input, not 'one-shot' magic. Effective use requires detailed specifications and context—essentially a modern, well-structured Product Requirements Document (PRD)—to guide the AI and minimize random, low-quality guesses.

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.

Product Requirement Documents (PRDs) are often written and then ignored. AI-generated prototypes change this dynamic by serving as powerful internal communication tools. Putting an interactive model in front of engineering and design teams sparks better, more tangible conversations and ideas than a flat document ever could.

The prompts for your "LLM as a judge" evals function as a new form of PRD. They explicitly define the desired behavior, edge cases, and quality standards for your AI agent. Unlike static PRDs, these are living documents, derived from real user data and are constantly, automatically testing if the product meets its requirements.

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.