Pigford finds more fulfillment building multiple products simultaneously, framing it as "feeding the beast" of his ADHD. This contrasts with traditional advice to focus on one thing, prioritizing personal fulfillment and learning over maximizing the profitability of a single venture.
Pigford developed a custom AI skill that acts as an adversarial check on the AI's own code. It's based on the premise that the AI "almost certainly screwed some stuff up," forcing it to re-evaluate and self-correct before human review, which consistently finds bugs.
Instead of relying on a single AI model, Josh Pigford's workflow uses Opus for initial code generation and then runs a review pass with a different powerful model like GPT. This adversarial, multi-model process consistently uncovers 3-5 bugs that the primary model overlooks.
Pigford built a meta-skill that reviews each development session, including conversations where he repeatedly corrected the AI. It then distills these corrections into a central project document, effectively teaching the AI agent not to make the same mistakes in future sessions.
Each feature is built in distinct, user-testable phases, and each phase uses a new, isolated work tree. This serves as a "save point," preventing context from one phase from corrupting the next, reducing hallucinations, and allowing for easy rollbacks if something goes wrong.
Pigford's process inverts the typical "marketing first" approach. He fully builds the product, then tasks an AI with analyzing its complete feature set to generate the marketing copy. This ensures the landing page is grounded in the final product's reality, not an initial concept.
Pigford argues against spending months building before launching. He's shipped products on the same day he had the idea, believing it's a "real bad idea" to delay. This speed is crucial for getting immediate user feedback to understand their problems, which often differ from a founder's assumptions.