Most people get bad AI output because they give AI a bad brief. This framework fixes that — permanently. Master these five ingredients and you'll get dramatically better results from any AI tool, every time.
Think of AI like a brilliant new hire on their first day. They're capable, fast, and eager — but they know nothing about your business, your customers, or what "good" looks like. Your prompt is their brief. The better you brief them, the better they perform.
The Role is the persona you assign to AI before it does anything. It's the single highest-leverage ingredient in the framework — changing the Role alone can completely transform the quality, tone, and expertise level of the output.
Context is the briefing. AI knows nothing about your business, your customer, what happened yesterday, or what's at stake — until you tell it. The more specific and relevant context you provide, the more useful and accurate the output.
The Task is the specific action you want AI to perform. Most people make their Task too vague — they ask for a "summary" when they mean a "3-bullet executive brief" or ask AI to "help with the email" when they mean "write a follow-up that reopens a stalled conversation."
Format controls the structure, length, tone, and style of what AI produces. Without explicit Format instructions, AI defaults to its own preferences — which are often too long, too formal, or structured in a way that doesn't match your actual use case.
Constraints are the guardrails. They protect your brand voice, prevent AI from using language you hate, and stop it from making assumptions that undermine the output. Most beginners skip this step. Experts never do.
Here's the same request — a sales follow-up email — with and without R·C·T·F·C. Read both outputs and decide which one you'd actually send.
The Prompt
The Prompt
Follow these steps every time. After about 20 prompts, the framework becomes instinctive — you'll stop thinking about the letters and start thinking directly in terms of what AI needs to know.
Every prompt below is fully built using R·C·T·F·C. Copy it, fill in the brackets, and run it. Then tweak one variable and run it again.
Every one of these is fixable with one more line in your prompt. Recognizing them is half the battle.
Save this. Print this. Screenshot this. The R·C·T·F·C Framework in the smallest possible format.
The R·C·T·F·C Framework is just the beginning. Our Role-Based Prompt Engineering Workshops build this into your team's muscle memory — with prompts built for your specific roles, workflows, and business.