🧪 TESTED BY ONLYFREEPROMPTS
Make My Prompt Better First
Turn a vague request into a prompt worth running—before the AI answers it.
It fixes ambiguity before generation, asks only decision-changing questions and lets you approve the rewritten prompt before spending time on the answer.
It fixes ambiguity before generation, asks only decision-changing questions and lets you approve the rewritten prompt before spending time on the answer. Results still depend on the model and the information you provide.
MAKE IT YOURS
Tell the prompt what it needs
YOUR PROMPT
889 charactersAct as a prompt editor before acting as an assistant. My rough prompt is: Make me a good presentation about our new service Do not perform the task yet. 1. State the likely goal in one sentence. 2. Identify only the ambiguities that would materially change the result. 3. Ask me no more than three concise questions. If safe, reasonable defaults are possible, propose them instead of asking. 4. After I answer, rewrite the prompt with a clear objective, audience, inputs, constraints, output structure, quality checks and any necessary uncertainty or safety limits. 5. Show the improved prompt in one copyable block, followed by a short list titled “What changed”. 6. Wait for me to approve or edit the prompt before doing the task. Do not inflate a simple request into an unnecessarily complicated workflow. Never invent missing facts or imply access to tools or data you do not have.
WHY TRY IT?
A model cannot reliably guess what success looks like. This makes it improve the brief before attempting the work.
Turn a vague request into a prompt worth running—before the AI answers it.
EXAMPLE RESULT
Likely goal: create a concise sales presentation for a defined audience. Three questions: Who is the audience? What action should they take? What facts must be included?
Use it when the task matters or when your first attempt keeps producing generic answers. Skip it for tiny one-line requests. The source is an archived 2024 meta-prompting example; our version uses the idea without requiring its old models or API code.
WHAT HAPPENED WHEN WE TESTED IT
It fixes ambiguity before generation, asks only decision-changing questions and lets you approve the rewritten prompt before spending time on the answer. Results still depend on the model and the information you provide.
We rewrote the viral version to be more honest, more useful and less likely to overclaim. The prompt above is our better version.
It prioritises current official sources, checks who actually controls the billing and gives the shortest route plus a ready-to-send fallback. Not 10/10: it still depends on web access, company cooperation and a human checking the final terms before cancelling.