Prompt Engineering
Every framework, with its fields, a real example, and guidance on when to use it — and when not to.
| Framework | Best For | Level |
|---|---|---|
| CO-STAR Won Singapore GPT-4 Competition | Business communication and marketing copy | Medium |
| CRAFT | Marketing copy and content creation | Medium |
| RISEN | Enterprise workflows with sequential steps | High |
| TRACE | Tasks where you have an example of the ideal output | High |
| APE | Quick, everyday prompts | Low |
| SPECS | Complex technical analysis and research tasks | High |
| RTF | Professional tasks where a role matters | Low |
| Google Prompt | Business and professional tasks | Low |
| Single Prompt Line | Quick factual lookups | Low |
Context · Objective · Style · Tone · Audience · Response
The Singapore GPT-4 competition winner. Maximum control over voice, audience, and output format.
Context · Role · Action · Format · Target
Role-based framing with a clear target audience. Great for marketing, copywriting, and creative work.
Role · Instructions · Steps · End Goal · Narrowing
Built for multi-step enterprise tasks. The Narrowing field keeps AI output on-track and within constraints.
Task · Request · Action · Context · Example
Show, don't tell. The Example field teaches the AI exactly what you want better than any description.
Action · Purpose · Expectation
Three fields, high impact. The fastest framework — ideal for everyday prompts before graduating to more complex structures.
Situation · Purpose · Expected Output · Context · Style
Detail-oriented and precise. The Expected Output field eliminates guesswork and is ideal for complex technical tasks.
Role · Task · Format
Minimum viable prompt structure. Three fields that cover the three most impactful variables in any prompt.
Task · Context · Persona
Developed and recommended by Google. Optimised for Gemini and professional workplace tasks.
One clear, direct sentence
No framework fields — just a single well-crafted sentence. Faster to write, still effective for simple queries.
A Framework Wizard helps you choose. Then optimize, dispatch to 25+ AI models, and run consensus analysis — free.
