Open object
The prompt builder: turn a vague ask into a strong one
A clear prompt is built from a few parts. Switch each one on and watch a generic request turn into a specific one, with a live strength reading and feedback on what each part adds.
A large language model doesn't understand your intent; it predicts likely text from patterns. That is why how you phrase a request shapes what you get back. Most strong prompts are built from the same handful of parts: a clear instruction, a role for the AI to take, the context it needs, an example to imitate, and the format you want the answer in.
Toggle each part below. The prompt on the right rebuilds as you go, and the strength meter responds. There is no single right answer; the point is to feel how each part changes the request.
Scenario: you want help understanding the nervous system. Add parts to sharpen the request.
The five parts
Your prompt
The five parts get you a strong first draft. Refining it is its own skill. Dr Leo S. Lo's CLEAR framework is a useful checklist for that second pass.
- Concise. Remove detail you do not need and keep the request specific.
- Logical. If the prompt has several parts, order them so the AI sees how they relate.
- Explicit. State the format, content, or scope you want.
- Adaptive. Adjust your prompt based on what the AI returned.
- Reflective. Keep evaluating prompts and responses to improve over time.
One caution before you lean on frameworks
Frameworks are scaffolding for when you are starting out. A growing view is that they matter less than they look. Your real advantage is understanding a task well enough to describe it plainly in your own words. As digital-literacy researcher Mike Caulfield put it after an elaborate, multi-step prompt made his results worse: "Stop thinking about how to prompt, and start thinking about how to do things." Know your subject, say clearly what you want, and you rarely need the acronyms.