A defined workflow beat every clever prompt I wrote

Description and use

<p>When I started ParkEase I spent a lot of energy on prompts. Long ones. "You are a senior engineer who…", step lists, examples, warnings in capitals.</p> <p>They helped for about one session.</p> <p>The thing that actually changed the quality of the AI's output wasn't a better prompt. It was a workflow the AI couldn't talk its way around: fixed phases, named gates, and a rule that skipping one had to be said out loud. Here's why that works better, and three times it caught something I'd have shipped.</p> <h2> Why prompts don't scale </h2> <p>A prompt is a request. The model weighs it against

Problem

<p>When I started ParkEase I spent a lot of energy on prompts. Long ones. "You are a senior engineer who…", step lists, examples, warnings in capitals.</p> <p>They helped for about one session.</p> <p>The thing that actually changed the quality of the AI's output wasn't a better prompt. It was a workflow the AI couldn't talk its way around: fixed phases, named gates, and a rule that skipping one had to be said out loud. Here's why that works better, and three times it caught something I'd have shipped.</p> <h2> Why prompts don't scale </h2> <p>A prompt is a request. The model weighs it against

Outcome

<p>When I started ParkEase I spent a lot of energy on prompts. Long ones. "You are a senior engineer who…", step lists, examples, warnings in capitals.</p> <p>They helped for about one session.</p> <p>The thing that actually changed the quality of the AI's output wasn't a better prompt. It was a workflow the AI couldn't talk its way around: fixed phases, named gates, and a rule that skipping one had to be said out loud. Here's why that works better, and three times it caught something I'd have shipped.</p> <h2> Why prompts don't scale </h2> <p>A prompt is a request. The model weighs it against

Evidence

A defined workflow beat every clever prompt I wrote

Source