A powerful but unintuitive AI development pattern is to give a model a vague goal and let it attempt a full implementation. This "throwaway" draft, with its mistakes and unexpected choices, provides crucial insights for writing a much more accurate plan for the final version.
In an age of rapid AI prototyping, it's easy to jump to solutions without deeply understanding the problem. The act of writing a spec forces product managers to clarify their thinking and structure context. Writing is how PMs "refactor their thoughts" and avoid overfitting to a partially-baked solution.
A powerful workflow is to explicitly instruct your AI to act as a collaborative thinking partner—asking questions and organizing thoughts—while strictly forbidding it from creating final artifacts. This separates the crucial thinking phase from the generative phase, leading to better outcomes.
Even for a simple personal project, starting with a Product Requirements Document (PRD) dramatically improves the output from AI code generation tools. Taking a few minutes to outline goals and features provides the necessary context for the AI to produce more accurate and relevant code, saving time on rework.
Non-technical founders using AI tools must unlearn traditional project planning. The key is rapid iteration: building a first version you know you will discard. This mindset leverages the AI's speed, making it emotionally easier to pivot and refine ideas without the sunk cost fallacy of wasting developer time.
Instead of providing a vague functional description, feed prototyping AIs a detailed JSON data model first. This separates data from UI generation, forcing the AI to build a more realistic and higher-quality experience around concrete data, avoiding ambiguity and poor assumptions.
Borrowing from classic management theory, the most effective way to use AI agents is to fix problems at the earliest 'lowest value stage'. This means rigorously reviewing the agent's proposed plan *before* it writes any code, preventing costly rework later on.
Instead of aiming for a perfect AI-generated first draft, use it as a tool to overcome writer's block. When feeling unmotivated, ask an AI to produce an initial version. The often-flawed or "terrible" output can provide the necessary energy and motivation for a human writer to jump in and improve it.
Instead of writing detailed Product Requirement Documents (PRDs), use a brief prompt with an AI tool like Vercel's v0. The generated prototype immediately reveals gaps and unstated assumptions in your thinking, allowing you to refine requirements based on the AI's 'misinterpretations' before creating a clearer final spec.
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.
To prevent AI coding assistants from hallucinating, developer Terry Lynn uses a two-step process. First, an AI generates a Product Requirements Document (PRD). Then, a separate AI "reviewer" rates the PRD's clarity out of 10, identifying gaps before any code is written, ensuring a higher rate of successful execution.