Start here · 3:12
The best prompt is often a conversation
This lesson explains what a prompt framework is and why the strongest prompts start with the AI asking you questions instead of guessing at missing context.
- A prompt is the request you type into an AI tool such as ChatGPT, Claude or Gemini. A prompt framework is a reusable structure for that request, usually a short checklist named with an acronym so it is easy to remember.
- Frameworks help because the AI fills in whatever you leave out with generic guesses. A framework makes sure you include the parts that change the answer, such as who it is for, what you want to achieve and the format you need.
- Frameworks make prompts repeatable. You fill the same parts each time, save the prompt as a template and share it with colleagues, so a good result can be reproduced by anyone on the team.
- Frameworks are not magic words. The value comes from the detail you put in each part. They help most when a request is complex or open to interpretation, and a quick, simple question can stay short.
- There are well over sixty named frameworks, and most of them remix the same ingredients. Role, task, context, audience, format, constraints and examples appear again and again under different names.
- Most bad answers come from missing context you did not know was missing. OpenAI's guidance says the same for agents: do not guess details, ask for missing information. Interview-first prompting turns that into a habit.
| Term | Plain meaning | Example |
|---|---|---|
| Prompt | The request you type into an AI tool | Write my pricing page copy |
| Framework | A reusable checklist for that request | CRIT, RODES |
| Ingredient | One part of a good prompt | Role, task, context, format |
| Interview-first | AI asks before it writes | Ask me five questions first |
| Template | A saved prompt you reuse and share | Team pricing prompt |
Do this in your own tools, step by step. Ticks are saved on this device.
What is a prompt framework?
A reusable structure or checklist for the request you type into an AI tool.
Why do most bad answers happen?
Missing context you did not know was missing, so the AI guesses.
What does OpenAI's guidance say for agents?
Do not guess details, ask for missing information.
Paula Welcome to CRIT and RODES: Let the AI Ask You First. This course is part of Complete AI Training; you'll find the full library at complete A I training dot com. It takes six short chapters.
Abby Most bad answers come from context you never knew was missing. This part shows why the strongest prompts start with the AI asking you questions first.
Paula A prompt is the request you type into an AI tool such as ChatGPT, Claude or Gemini. A prompt framework is a reusable structure for that request. Think of it as a short checklist of the parts a good prompt contains, usually named with an acronym so it is easy to remember.
Abby Why does a framework help. The AI fills in whatever you leave out with generic guesses. A framework makes sure you include the parts that change the answer, such as who it is for, what you want to achieve and the format you need.
Paula Frameworks also make prompts repeatable. You fill the same parts each time, save the prompt as a template and share it with colleagues. They are not magic words. The value comes from the detail you put in each part, and they help most when a request is complex or open to interpretation. A quick, simple question can stay short.
Abby There are well over sixty named frameworks, and most of them remix the same ingredients. Role, task, context, audience, format, constraints and examples. CRIT and RODES, the two frameworks in this course, are fill-in-the-slots frameworks. Each letter stands for one part of your prompt.
Paula Now the problem this course solves. Most bad answers come from missing context you did not know was missing. You cannot write down what you forgot. So instead of guessing at your request, these frameworks make the AI ask questions before it starts.
Abby Here is the shape of it. You give a short brief. The AI asks you a few targeted questions. You answer. Then it writes. OpenAI's guidance says the same for agents. Do not guess details, ask for missing information. A conversation beats a guess every time.
Paula Here is how that looks inside a real tool. A small business owner wants a pricing page. The prompt sets the role, the task and the context, then asks the AI to interview them first. Notice the final line. It tells the AI to ask before writing.
Abby Watch what comes back. The AI does not write the page yet. It asks what it genuinely needs. What are your three tiers and prices. Do you offer a free trial or a first call. What is the one objection clients raise most. You answer in a line or two, and the copy lands on target.
Paula So the takeaway for this part. The best prompt is often a conversation. You do not need to know everything up front. Give a short brief, let the AI ask, then answer. That is the habit the rest of this course builds on.
Abby Your turn. Pick one real task from your job this week. Write a short brief with a role, a task and a context line, then add one instruction telling the AI to ask you questions before it writes. Answer its questions and read the result.
Get the other 5 chapters, the exam and your certificate for LinkedIn, plus all 700+ AI courses.