Prompting as a Design Skill: From “Try This” to Repeatable Patterns

AI output isn’t mysterious; it’s measurable. When we prompt like we’re chatting, we get content that feels generic and unpredictable. When we prompt like instructional designers, with audience, outcomes, constraints, and a definition of “good,” the same AI tool starts producing drafts you can actually reuse.

In this episode, Jackie walks through a simple mindset shift that changes everything: a prompt is a mini design document. From there, we name the three biggest reasons one-off prompts fail (vague goals, missing context, and no quality target) and replace them with three repeatable prompting patterns you can use across onboarding, microlearning, scenario design, job aids, and eLearning outlines. You’ll get a clear spec prompt formula for fast first drafts, a critique prompt to evaluate and rewrite with intention, and a variations prompt to create multiple options without starting over.

We also turn the patterns into a five-minute “prompt pack” you can keep in a notes app, plus one rule that prevents chaos in your AI workflow: change one thing at a time. 

Subscribe, share this with a fellow designer, and leave a review so more instructional designers can make AI feel like a skill instead of guesswork.

🔗 Episode Links

Please check out the resource mentioned in the episode. Enjoy!

Prompting Patterns Compass 

Join PodMatch!
Use the link to join PodMatch, a place for hosts and guests to connect.

Disclaimer: This post contains affiliate links. If you make a purchase, I may receive a commission at no extra cost to you.

Transcript

Welcome & Series Setup

Jackie Pelegrin 0:00

Hello, and welcome to the Designing with Love Podcast. I am your host, Jackie Pelegrin, where my goal is to bring you information, tips, and tricks as an instructional designer. Hello, instructional designers and educators. Welcome to episode 117 of the Designing with Love Podcast. As we continue through the 2026 lineup, we're also moving through the AI Ready Designer Series. Last time we built an AI QA mindset so you can catch errors and drift early. Today we'll turn prompting into reusable patterns so your outputs get better on purpose, not by luck. So grab your notebook, a cup of coffee, and settle in as we explore this topic together. Before we jump in, a quick note. This is a 12-episode arc, and each episode builds on the last. In this 12-episode AI ready designer series, we'll move through five AI ready checkpoints each time. So you always leave with something practical you can apply right away. Alright, let's jump into checkpoint one. Here's the shift. AI output quality isn't random. It's heavily influenced by the input. And that means prompting is becoming a real practical skill for instructional designers. When you treat prompts like casual requests, try this, make it better, write me a lesson, you get unpredictable results. But when you treat prompts like design specs, you get consistency. Here's your anchor line. A prompt is a mini design document. So if prompting is a skill, the next question is, what stays true about good design no matter what tool you're using? The constant is this quality comes from clarity. Just like we don't build instruction without audience, context, and outcomes, AI doesn't produce strong outputs without those inputs either. So the designer mindset stays the same. Define intent, define constraints, define success, and iterate with feedback. AI doesn't replace that. AI rewards it. And when clarity is missing, the problems show up in predictable ways. So let's name the risks. One off prompting fails for three reasons. Reason number one, vague goals. If you ask for a better outline, the tool has to guess what better means. Reason number two, missing context. No audience, no setting, no tone, and no constraints. So you get generic output. Reason number three, no quality target. If you don't define what good looks like, you can't reliably get it. So the risk isn't that AI is bad. The risk is that we prompt it like we're chatting, instead of prompting like we're designing. The good news is you don't need a hundred clever prompts. You need a few repeatable patterns. Here are three patterns you can reuse across projects. Pattern number one, the spec prompt. Use when you want clean, usable prompts fast. Here's the formula. Role, audience, goal, constraints, and format. Now here's an example. You're an instructional designer, audience is new hires. Goal is to reduce common errors. Constraints. Five minutes, plain language, accessible. Format outline with three sections and a quick practice activity. Pattern number two. The critique prompt. Use when you already have a draft and want it better on purpose. Here's the formula. Include the draft, evaluate using criteria, and suggest revisions. Now here's an example. Review this outline for clarity, alignment to outcomes, and opportunities for practice plus feedback. Then rewrite it with these improvements. Pattern number three, the variations prompt. Use when you want multiple versions without reinventing. Here's the formula. Create three options, keep constants, and vary one dimension. Now here's an example. Create three scenario options. Keep the same objective and tone. Vary the difficulty level. Easy, medium, and hard. Now let's turn those patterns into a quick system you can apply in under five minutes. Here's your simple prompt pack you can keep in a notes app. Spec prompt, first draft, critique prompt, quality upgrade, and variations prompt, options fast. And here's the rule that prevents chaos. Change one thing at a time. If you change the audience and tone and format, you won't know what caused the improvement. Let me give you a quick field note so you can see what this looks like in the real world. A designer needs a micro lesson fast. The first prompt is vague and the output is generic. So they switch to the spec pattern, audience, goal, constraints, and format. Then they run the critique pattern, check alignment, clarity, and practice. Finally, they run variations, three scenario options at different difficulty levels. Same tool, completely different result, because the prompt became a design spec. Alright, let's make this actionable with a simple challenge you can do this week. Here's your checkpoint challenge for this week. Save three prompts in a notes app. One spec prompt, one critique prompt, and one variations prompt. And then use them once on a real project and compare the output to your try this prompts. Alright, if you want this to feel easier next time, I have a quick tool for you. Before you go, I made an interactive companion called Prompting Patterns Compass. It's a quick click-through guide you can use to build better prompts on purpose and get more consistent results. If this episode helped you, please follow or subscribe and share it with a designer who wants AI to feel less like guesswork and more like a skill. Prompting isn't a trick, it's a design skill. When you give the tool a clear goal, real constraints, and a format, you get outputs you can trust and reuse. Before I conclude this episode, here's an inspiring quote by James Clear. You do not rise to the level of your goals. You fall to the level of your systems. Thanks for spending time with me today. Until next time, keep it practical, keep it human, and keep designing with love. Thank you for taking some time to listen to this podcast episode today. Your support means the world to me. If you'd like to help keep the podcast going, you can share it with a friend or colleague, leave a heartfelt review, or offer a monetary contribution. Every act of support, big or small, makes a difference, and I'm truly thankful for you.